© 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. 15207
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific place or person named Clark

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Clark."

    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
    choes
    -0.83
    awaru
    -0.76
    urity
    -0.74
    req
    -0.70
    qs
    -0.70
    ntil
    -0.69
    orescence
    -0.69
    gur
    -0.69
    76561
    -0.66
    λ
    -0.66
    POSITIVE LOGITS
    stown
    0.99
    ston
    0.93
     Kent
    0.93
    obyl
    0.90
     Ashton
    0.85
    istically
    0.81
    istics
    0.80
    istic
    0.80
     County
    0.79
     Gregg
    0.78
    Activations Density 0.026%

    No Known Activations