© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33362
    Prev
    Next
    INDEX
    Explanations

    jargon and concepts related to theoretical discussions in academic texts, particularly in the fields of economics, mathematics, philosophy, and physics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.12
    0.6%
    578
    +0.10
    0.5%
    404
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.17
    622
    +0.10
    0.06
    734
    +0.10
    0.08
    Negative Logits
    xes
    -0.67
    velt
    -0.66
    worthy
    -0.65
    cake
    -0.64
    ridge
    -0.64
    rooms
    -0.63
    wick
    -0.63
    ards
    -0.62
    winner
    -0.62
    win
    -0.62
    POSITIVE LOGITS
    ities
    0.87
    ity
    0.78
     physicist
    0.76
    ité
    0.76
     physicists
    0.67
     explor
    0.67
     frameworks
    0.65
     significance
    0.65
     underpin
    0.64
     feasibility
    0.63
    Activations Density 4.852%

    No Known Activations