© 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. 23215
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities involved in specific events or contexts

    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
     swall
    -0.86
    senal
    -0.82
     swallow
    -0.75
     Wiley
    -0.73
     swallowing
    -0.72
     Sorceress
    -0.72
    ModLoader
    -0.72
     Coffin
    -0.72
     candle
    -0.71
     metic
    -0.69
    POSITIVE LOGITS
    ari
    1.18
    arius
    0.95
    omen
    0.95
    aris
    0.93
    ord
    0.92
    ARI
    0.87
    orne
    0.86
    ius
    0.83
    ORD
    0.82
    gression
    0.79
    Activations Density 0.259%

    No Known Activations