Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4526
    Prev
    Next
    INDEX
    Explanations

    terms related to commerce or organizations with the abbreviation "Comm"

    oai_token-act-pair · gpt-3.5-turbo

    references to committees and commissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.78
    uca
    -0.68
    ly
    -0.68
     Wolver
    -0.68
    books
    -0.65
    yon
    -0.64
     Lump
    -0.62
    conom
    -0.62
     Lan
    -0.62
    hua
    -0.60
    POSITIVE LOGITS
    ork
    0.76
    antes
    0.74
    arij
    0.71
    unal
    0.71
    issions
    0.70
    efficient
    0.69
    ENCE
    0.69
    onsense
    0.69
    ortal
    0.67
    rontal
    0.65
    Activations Density 0.087%

    No Known Activations