© 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. 11-RES-JB
    11. 7091
    Prev
    Next
    INDEX
    Explanations

    mentions of death or fatal incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.86
    rium
    -0.75
    idth
    -0.69
    osterone
    -0.62
    Bir
    -0.59
    CHAT
    -0.58
    osit
    -0.58
    users
    -0.58
    GY
    -0.57
    ertain
    -0.56
    POSITIVE LOGITS
     by
    1.05
     accidentally
    0.90
     instantly
    0.89
     fighting
    0.83
     tragically
    0.82
     during
    0.80
     rampage
    0.77
     unintentionally
    0.76
     violently
    0.75
     mysteriously
    0.75
    Activations Density 0.069%

    No Known Activations