© 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. 6-RES-JB
    11. 5570
    Prev
    Next
    INDEX
    Explanations

    phrases related to filling in or completion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "fill in" related to completing information or forms

    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
    Unix
    -0.84
     DRAG
    -0.73
    edu
    -0.73
    -+
    -0.72
    FML
    -0.67
    MODE
    -0.67
     mathemat
    -0.66
    MQ
    -0.63
    ONSORED
    -0.62
     Phi
    -0.61
    POSITIVE LOGITS
    iston
    0.78
     coffers
    0.77
    auga
    0.75
     captcha
    0.69
    abor
    0.69
     prescriptions
    0.66
    burgh
    0.65
    erton
    0.65
     pockets
    0.64
    erella
    0.64
    Activations Density 0.048%

    No Known Activations