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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 22426
    Prev
    Next
    INDEX
    Explanations

    specific references or citations within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to formal citations or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nut
    -0.84
     Tycoon
    -0.80
    hm
    -0.73
     independ
    -0.72
    hma
    -0.71
    enthal
    -0.70
    anyahu
    -0.70
    pher
    -0.70
    kish
    -0.70
    nu
    -0.68
    POSITIVE LOGITS
     citation
    1.60
     citations
    1.29
     Citation
    1.08
     cited
    0.82
     footnote
    0.82
    ibli
    0.81
    Footnote
    0.81
     cite
    0.77
     Forbidden
    0.75
    ENC
    0.74
    Activations Density 0.015%

    No Known Activations