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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 20317
    Prev
    Next
    INDEX
    Explanations

    references to legal acts and legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative acts or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scion
    -0.70
     Prin
    -0.70
     unin
    -0.64
     Conan
    -0.62
    birds
    -0.61
    acid
    -0.60
     unnamed
    -0.59
     Niet
    -0.59
    stocks
    -0.59
    Crystal
    -0.59
    POSITIVE LOGITS
     Amendments
    1.28
    uary
    1.06
     Implementation
    0.87
    iard
    0.83
     Amendment
    0.81
     enacted
    0.81
     1958
    0.79
    rine
    0.76
     provisions
    0.76
     amendments
    0.75
    Activations Density 0.042%

    No Known Activations