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. 11-RES-JB
    6. 17978
    Prev
    Next
    INDEX
    Explanations

    statements or questions related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes and considerations

    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
     Mare
    -0.72
    STAT
    -0.72
    aud
    -0.71
     Cah
    -0.69
     Walls
    -0.69
    enium
    -0.69
     Schwe
    -0.68
     Meng
    -0.68
    eport
    -0.67
     Stam
    -0.67
    POSITIVE LOGITS
     choice
    2.11
    Choice
    2.01
     choices
    1.99
    choice
    1.95
     Choice
    1.94
     choosing
    1.89
     choose
    1.82
     selection
    1.77
     selections
    1.74
     chose
    1.73
    Activations Density 0.416%

    No Known Activations