© 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. 35686
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    480
    +0.25
    1.2%
    87
    +0.14
    0.7%
    350
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.25
    -0.10
    266
    +0.14
    0.33
    325
    +0.13
    0.10
    Negative Logits
    ufact
    -0.67
     skim
    -0.64
     gobl
    -0.59
    artney
    -0.58
    pload
    -0.58
    ccording
    -0.57
     fertil
    -0.57
    umenthal
    -0.56
    HAHAHAHA
    -0.56
     referen
    -0.56
    POSITIVE LOGITS
    meter
    0.65
    çļ
    0.64
     Telescope
    0.64
     Modes
    0.63
    igraph
    0.60
    enment
    0.59
    java
    0.58
    mess
    0.57
    ws
    0.56
    axies
    0.55
    Activations Density 17.640%

    No Known Activations