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. 4-RES-JB
    6. 19193
    Prev
    Next
    INDEX
    Explanations

    keywords related to choices, strategies, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    terms related to options and choices in various contexts

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

    No Comments

    Negative Logits
     Educ
    -0.85
     Obesity
    -0.77
    ombat
    -0.77
     Poverty
    -0.75
     Supplement
    -0.72
    imb
    -0.72
     Conduct
    -0.72
     Hemp
    -0.71
     Degree
    -0.71
    cert
    -0.70
    POSITIVE LOGITS
     signings
    1.11
     backfield
    1.02
     hitters
    0.87
     roster
    0.86
     forwards
    0.86
     rook
    0.84
     keeper
    0.84
     outfield
    0.82
     hitter
    0.82
     rosters
    0.82
    Activations Density 0.115%

    No Known Activations