© 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. 11-RES-JB
    11. 13205
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    connectors and conjunctions related to public service discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oward
    -0.82
    sed
    -0.78
    tein
    -0.78
    astical
    -0.74
    uper
    -0.70
    burgh
    -0.70
    UAL
    -0.67
    itud
    -0.66
    AIN
    -0.66
    pez
    -0.65
    POSITIVE LOGITS
     therefore
    1.36
     hence
    1.25
     thus
    1.12
     consequently
    1.09
     shouldn
    0.97
     furthermore
    0.96
     deserves
    0.95
     cannot
    0.95
     moreover
    0.88
     whoever
    0.88
    Activations Density 0.207%

    No Known Activations