© 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. 145
    Prev
    Next
    INDEX
    Explanations

    words related to specific alphanumeric characters or technical terms in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or organizations

    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
    otaur
    -0.75
    hens
    -0.73
    DragonMagazine
    -0.73
    ortment
    -0.73
     subcontract
    -0.73
    anwhile
    -0.72
     Canaver
    -0.70
    enhagen
    -0.70
    endium
    -0.66
    ierrez
    -0.66
    POSITIVE LOGITS
    ¹
    1.24
    £
    1.09
    ¨
    1.06
    ±
    1.03
    ¥
    0.99
     Ø
    0.97
    Ĥ
    0.95
    Ù
    0.95
    º
    0.93
    ³
    0.92
    Activations Density 0.003%

    No Known Activations