Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13796
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "screw" and related terms or contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    151
    +0.14
    0.5%
    277
    +0.13
    0.5%
    365
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.09
    48
    +0.13
    0.07
    232
    +0.13
    0.06
    Negative Logits
    RED
    -0.89
    oma
    -0.89
    vim
    -0.88
    ators
    -0.86
    omas
    -0.86
    olithic
    -0.85
    omorph
    -0.84
    ologne
    -0.83
    cept
    -0.83
    ãĥ´
    -0.82
    POSITIVE LOGITS
    driver
    1.29
    drivers
    1.15
    sie
    1.05
    shake
    1.01
    ritten
    0.97
    yrights
    0.93
    flake
    0.89
    ball
    0.89
    sch
    0.88
     goof
    0.87
    Activations Density 1.255%

    No Known Activations