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 Local
    5. 6-RES_SCL-AJT
    6. 13344
    Prev
    Next
    INDEX
    Explanations

    questions related to biased reporting in media stories

    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
    121
    +0.05
    0.5%
    276
    +0.05
    0.5%
    285
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.05
    0.05
    31
    +0.05
    0.10
    701
    +0.04
    0.05
    Negative Logits
    senal
    -0.32
    abuse
    -0.31
    condition
    -0.31
    govtrack
    -0.31
    dyl
    -0.30
    otropic
    -0.30
    udeb
    -0.30
    ModLoader
    -0.29
    ngth
    -0.28
    ccording
    -0.27
    POSITIVE LOGITS
    sburgh
    0.43
    lett
    0.35
    aneous
    0.35
    sburg
    0.32
    stown
    0.31
     Alto
    0.31
     Mechdragon
    0.31
     Stephenson
    0.29
    esy
    0.29
    nance
    0.28
    Activations Density 10.487%

    No Known Activations