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. 8-RES-JB
    6. 21535
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period followed by a high-level domain abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    sentences or clauses indicating strong statements or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Bracket Closing Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
    onga
    -0.74
    mega
    -0.61
    ¯¯
    -0.59
    agnetic
    -0.58
    ãĢIJ
    -0.57
    ãĢİ
    -0.56
    ishable
    -0.56
     IPM
    -0.56
     commod
    -0.55
    ibaba
    -0.54
    POSITIVE LOGITS
     .)
    1.93
    .)
    1.89
    .")
    1.80
    .).
    1.75
    .),
    1.75
    .):
    1.74
    .]
    1.66
    ?)
    1.65
    !)
    1.65
    â̦)
    1.59
    Activations Density 0.360%

    No Known Activations