© 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. 10-RES-JB
    11. 9869
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities with a focus on names and titles

    oai_token-act-pair · gpt-3.5-turbo

    specific names or proper nouns, particularly related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reply
    -0.80
     commissions
    -0.62
     bearer
    -0.61
     reckoning
    -0.60
     autistic
    -0.59
    veland
    -0.59
     CPR
    -0.57
     cryst
    -0.57
     ply
    -0.56
     amber
    -0.56
    POSITIVE LOGITS
    bilt
    0.88
    export
    0.80
    sov
    0.79
    rius
    0.73
    amins
    0.73
    ovich
    0.72
    Leaks
    0.71
    kov
    0.71
    iev
    0.69
    ennes
    0.69
    Activations Density 0.217%

    No Known Activations