© 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. 20319
    Prev
    Next
    INDEX
    Explanations

    surnames of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    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
    ש
    -0.61
     AAA
    -0.61
     Thumbnails
    -0.59
    ERAL
    -0.58
    sembly
    -0.57
    Roaming
    -0.54
    ournal
    -0.53
     Cerberus
    -0.52
     Yugoslav
    -0.51
    ccording
    -0.51
    POSITIVE LOGITS
    gren
    0.86
    meier
    0.84
    ville
    0.83
    ston
    0.83
     County
    0.83
     et
    0.80
    hurst
    0.79
    sey
    0.79
     Creek
    0.78
    quist
    0.78
    Activations Density 0.240%

    No Known Activations