© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14865
    Prev
    Next
    INDEX
    Explanations

    words related to arbitrariness or decisions

    oai_token-act-pair · gpt-3.5-turbo

    words related to digital information technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.89
     mosqu
    -0.78
     bands
    -0.77
    ammad
    -0.75
    rouse
    -0.69
     tiss
    -0.69
     phyl
    -0.68
     tremend
    -0.68
    anguage
    -0.68
    ¥µ
    -0.65
    POSITIVE LOGITS
    terness
    1.12
    coins
    0.94
    ertodd
    0.93
    ches
    0.86
    rarily
    0.86
    unia
    0.78
    buck
    0.77
    opia
    0.77
    rary
    0.76
    bite
    0.75
    Activations Density 0.005%

    No Known Activations