© 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 EvalsExportsinterp-engineNEWAPI 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. 31610
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical symbols related to 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
    447
    +0.12
    0.6%
    710
    +0.10
    0.5%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.12
    0.11
    167
    +0.10
    -0.03
    743
    +0.10
    0.07
    Negative Logits
    abouts
    -0.65
    rill
    -0.65
    stic
    -0.64
    odore
    -0.61
    rising
    -0.59
    Chall
    -0.59
    lahoma
    -0.59
    hower
    -0.59
    lov
    -0.59
    ril
    -0.58
    POSITIVE LOGITS
    PP
    0.89
    GS
    0.82
    PC
    0.81
    SI
    0.81
    cknowled
    0.76
    FS
    0.76
    WP
    0.76
    VP
    0.76
    MM
    0.76
    OTO
    0.75
    Activations Density 12.138%

    No Known Activations