© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23380
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the word "Look", often indicating a call to direct attention or emphasis on a particular point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "look"

    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
    EStreamFrame
    -0.85
    cffff
    -0.76
    stem
    -0.72
    orb
    -0.71
    âĹ¼
    -0.67
    actionDate
    -0.67
    scribed
    -0.64
    estinal
    -0.62
    KEN
    -0.62
    iHUD
    -0.61
    POSITIVE LOGITS
    ahead
    0.92
    ups
    0.83
    ings
    0.83
    INGS
    0.83
    outs
    0.83
    atio
    0.78
    ared
    0.73
     Ahead
    0.73
    ies
    0.72
    able
    0.68
    Activations Density 0.036%

    No Known Activations