© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24220
    Prev
    Next
    INDEX
    Explanations

    phrases related to filling out forms or questionnaires

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "fill out" in various contexts related to completing forms or applications

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

    No Comments

    Negative Logits
    esa
    -0.71
    Corp
    -0.68
    antry
    -0.67
    Edited
    -0.61
     sled
    -0.61
    inki
    -0.60
     stir
    -0.59
    aic
    -0.58
     Mub
    -0.57
    ioned
    -0.56
    POSITIVE LOGITS
    )=(
    0.86
    stretched
    0.85
    wagen
    0.84
    ricular
    0.81
    wards
    0.80
    flows
    0.79
    fitted
    0.76
    lier
    0.75
    ubis
    0.75
    doors
    0.74
    Activations Density 0.068%

    No Known Activations