© 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. 4-RES-JB
    11. 7612
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific places or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or locations

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

    No Comments

    Negative Logits
    oured
    -0.77
     Apostles
    -0.76
    mount
    -0.73
    天
    -0.70
    gemony
    -0.69
    ently
    -0.67
    AGE
    -0.63
    hett
    -0.61
    ouring
    -0.61
     Aval
    -0.60
    POSITIVE LOGITS
    imura
    0.87
    gnu
    0.87
    sth
    0.80
    isites
    0.78
    emort
    0.77
    thread
    0.76
    jiang
    0.75
    ikuman
    0.75
    zers
    0.75
    san
    0.75
    Activations Density 0.016%

    No Known Activations