© 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 EvalsExportsAPI 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. 16823
    Prev
    Next
    INDEX
    Explanations

    phone numbers or numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    high numerical values or percentages

    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
    eworks
    -0.88
    istically
    -0.69
    stem
    -0.68
    matically
    -0.68
    odynam
    -0.66
    boarding
    -0.66
    odynamic
    -0.65
    ItemImage
    -0.63
    board
    -0.62
    igating
    -0.62
    POSITIVE LOGITS
    999
    1.28
    LECT
    0.92
    aire
    0.86
    089
    0.81
    ¢
    0.79
    %:
    0.78
    CRIP
    0.76
    %-
    0.76
    onso
    0.75
    090
    0.75
    Activations Density 0.031%

    No Known Activations