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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4297
    Prev
    Next
    INDEX
    Explanations

    instances of statements related to taking opportunities or chances

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attempts or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reements
    -0.81
    nih
    -0.79
    iona
    -0.70
    nc
    -0.69
    ecause
    -0.69
    reek
    -0.68
    hesis
    -0.67
    nces
    -0.67
    row
    -0.67
    resa
    -0.66
    POSITIVE LOGITS
     greatness
    0.80
     fame
    0.79
     paradise
    0.74
     madness
    0.69
     Wonderland
    0.69
     whats
    0.69
     anything
    0.68
     tasty
    0.63
     riches
    0.63
     whatever
    0.62
    Activations Density 0.195%

    No Known Activations