© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12581
    Prev
    Next
    INDEX
    Explanations

    references to figures and technical details in scientific context

    oai_token-act-pair · gpt-3.5-turbo

    references to figures or illustrations in the document

    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
    minist
    -0.73
    ntil
    -0.72
     polic
    -0.70
    ances
    -0.69
    izabeth
    -0.68
    itability
    -0.67
     vow
    -0.66
    erker
    -0.66
    resist
    -0.65
    onte
    -0.65
    POSITIVE LOGITS
    Figure
    1.14
     Figure
    0.88
    Fig
    0.85
    Table
    0.83
     Drawing
    0.77
     largeDownload
    0.77
    books
    0.76
    Ī
    0.76
     Exhibit
    0.75
     macros
    0.75
    Activations Density 0.015%

    No Known Activations