© 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. 1-RES-JB
    11. 20063
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named Ryder

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or organizations associated with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.94
    uyomi
    -0.79
     newcom
    -0.77
    atoon
    -0.76
    umbn
    -0.71
    wart
    -0.70
    ileaks
    -0.70
    uchin
    -0.70
    nown
    -0.69
    plex
    -0.69
    POSITIVE LOGITS
     JD
    0.98
    JD
    0.92
    enger
    0.85
    DS
    0.83
     Ryder
    0.80
    aceae
    0.79
    Ze
    0.79
    ANCE
    0.78
    otle
    0.77
    iversary
    0.75
    Activations Density 0.023%

    No Known Activations