© 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. 1-RES-JB
    11. 16882
    Prev
    Next
    INDEX
    Explanations

    the word "clamp" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "clamp" and its variations, often related to control or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isconsin
    -0.77
    cloth
    -0.73
    living
    -0.71
    sweet
    -0.69
    hammad
    -0.68
    WP
    -0.67
    available
    -0.67
    WARD
    -0.67
    availability
    -0.67
    generation
    -0.66
    POSITIVE LOGITS
     clamp
    1.50
    downs
    0.87
     wrench
    0.86
     prick
    0.86
    amped
    0.81
    itudinal
    0.81
     overflow
    0.79
     stomp
    0.77
     overfl
    0.75
    hetti
    0.73
    Activations Density 0.009%

    No Known Activations