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. 6-RES-JB
    6. 14296
    Prev
    Next
    INDEX
    Explanations

    vague concepts and general statements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and conjunctions that connect thoughts or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsky
    -0.91
    ricanes
    -0.83
    aido
    -0.79
    å§«
    -0.78
    aunts
    -0.75
    undreds
    -0.73
    ases
    -0.73
    aults
    -0.72
    arsh
    -0.71
    ahime
    -0.71
    POSITIVE LOGITS
     hence
    0.87
     akin
    0.84
     therefore
    0.82
     moreover
    0.79
     wherein
    0.76
     requiring
    0.75
     meant
    0.75
     whereby
    0.74
     insofar
    0.74
     albeit
    0.73
    Activations Density 0.659%

    No Known Activations