© 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. 20129
    Prev
    Next
    INDEX
    Explanations

    names of different people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in significant events or incidents

    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
    ãĤ±
    -0.79
    oshenko
    -0.79
     Crate
    -0.75
    rett
    -0.74
    ãĥ¯
    -0.71
    uments
    -0.71
    strate
    -0.70
    д
    -0.69
    ãĥ¥
    -0.69
    ATES
    -0.66
    POSITIVE LOGITS
     Wick
    0.92
    sein
    0.90
     Hutchinson
    0.84
     Hutch
    0.82
    row
    0.76
    urdue
    0.75
     plur
    0.74
    emb
    0.74
    cliffe
    0.73
    ness
    0.71
    Activations Density 0.027%

    No Known Activations