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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 10641
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, specifically draft selections and picks

    oai_token-act-pair · gpt-3.5-turbo

    rankings or selections indicated by "overall" followed by a numerical value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulas
    -0.84
    rette
    -0.79
     Caf
    -0.76
     Speedway
    -0.71
    mosp
    -0.68
    erie
    -0.67
    Hyper
    -0.67
     Minute
    -0.67
    nee
    -0.66
     Cly
    -0.66
    POSITIVE LOGITS
    heastern
    0.89
     standings
    0.86
     averages
    0.82
    ikuman
    0.81
     constitu
    0.79
    gebra
    0.79
     overall
    0.74
    efficients
    0.73
     competitiveness
    0.73
     stability
    0.71
    Activations Density 0.010%

    No Known Activations