© 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. 32264
    Prev
    Next
    INDEX
    Explanations

    words related to strengths and weaknesses, especially focusing on strengths

    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
    +0.07
    0.7%
    285
    +0.04
    0.5%
    73
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.07
    0.10
    34
    +0.04
    0.07
    206
    +0.04
    0.08
    Negative Logits
    abad
    -0.31
    rolling
    -0.31
    URA
    -0.31
    rollers
    -0.31
    bus
    -0.28
    ICA
    -0.28
    dos
    -0.27
     boarding
    -0.27
    roller
    -0.27
    rary
    -0.27
    POSITIVE LOGITS
    heet
    0.32
     strengths
    0.31
     weaknesses
    0.31
     complement
    0.29
    cape
    0.28
     merits
    0.28
    ystem
    0.28
    ibilities
    0.28
     Weak
    0.28
    pring
    0.27
    Activations Density 12.518%

    No Known Activations