© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14151
    Prev
    Next
    INDEX
    Explanations

    references to legal acts or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prin
    -0.73
    stocks
    -0.65
     Niet
    -0.63
     Conan
    -0.63
     Scion
    -0.61
     Canaver
    -0.61
    hiba
    -0.61
     Trance
    -0.60
    axter
    -0.60
     experien
    -0.59
    POSITIVE LOGITS
     Amendments
    1.24
    uary
    1.15
     Implementation
    0.89
     1958
    0.88
    iard
    0.85
    ors
    0.83
     Amendment
    0.83
     enacted
    0.82
    rine
    0.80
     1903
    0.80
    Activations Density 0.039%

    No Known Activations