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. 22676
    Prev
    Next
    INDEX
    Explanations

    names of US Senators

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and conjunctions indicating a list of people or items

    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
    ento
    -0.74
    istical
    -0.73
    sson
    -0.72
     {\
    -0.69
    Ãį
    -0.68
    ":"/
    -0.68
    dx
    -0.68
    spring
    -0.67
    Stream
    -0.66
    istics
    -0.65
    POSITIVE LOGITS
     Dianne
    1.24
     Kirst
    1.23
     Tammy
    1.21
     Barbara
    1.18
     Debbie
    1.18
     Jeanne
    1.18
     John
    1.17
     Michele
    1.17
     Jeff
    1.16
     Richard
    1.16
    Activations Density 0.127%

    No Known Activations