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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 5340
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Look"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Look" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.86
    cffff
    -0.85
    orb
    -0.83
    âĹ¼
    -0.76
    stem
    -0.73
    iHUD
    -0.66
     rink
    -0.65
    actionDate
    -0.64
    éĹ
    -0.64
    ricular
    -0.64
    POSITIVE LOGITS
    ahead
    0.90
    ings
    0.88
    INGS
    0.85
    atio
    0.79
    ups
    0.78
    outs
    0.76
    ared
    0.74
    ies
    0.69
    ingly
    0.69
    points
    0.68
    Activations Density 0.032%

    No Known Activations