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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17438
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "How many"

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about quantities or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acus
    -0.85
    akings
    -0.73
    andr
    -0.72
    ocracy
    -0.71
    hern
    -0.70
    ħĭ
    -0.69
    instead
    -0.69
    bringing
    -0.68
    FontSize
    -0.67
    UAL
    -0.66
    POSITIVE LOGITS
     times
    1.04
     iterations
    0.84
     facets
    0.78
    ones
    0.76
    body
    0.75
    een
    0.74
     repet
    0.73
     dozen
    0.73
     people
    0.71
     miles
    0.70
    Activations Density 0.042%

    No Known Activations