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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 67
    Prev
    Next
    INDEX
    Explanations

    time references such as specific hours, minutes, and dates

    oai_token-act-pair · gpt-3.5-turbo

    time-related information and timings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorpor
    -0.68
    verages
    -0.67
     Baton
    -0.65
     Tucson
    -0.65
    comb
    -0.64
    Columb
    -0.63
     helicop
    -0.63
     spons
    -0.62
     psychiat
    -0.61
    FontSize
    -0.61
    POSITIVE LOGITS
    Dialogue
    0.80
     Dialogue
    0.77
     <@
    0.75
    ropy
    0.74
    _>
    0.73
    SAY
    0.71
     <+
    0.70
    anian
    0.68
    ools
    0.67
    EMOTE
    0.67
    Activations Density 0.060%

    No Known Activations