© 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. 8-RES-JB
    11. 9058
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Tony."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tony."

    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
    INESS
    -0.89
    ãģ¦
    -0.78
    ername
    -0.76
    words
    -0.75
    baugh
    -0.74
    arettes
    -0.72
    BOOK
    -0.71
    earance
    -0.69
    fulness
    -0.69
    Roaming
    -0.69
    POSITIVE LOGITS
     Sop
    1.00
     Abbott
    0.95
     Blair
    0.93
     Fernand
    0.91
     Hawk
    0.89
     Romo
    0.88
    isations
    0.79
    izations
    0.76
     Stark
    0.75
    ized
    0.73
    Activations Density 0.021%

    No Known Activations