© 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. 6129
    Prev
    Next
    INDEX
    Explanations

    political and social issues or controversies

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and relational conjunctions within complex sentences

    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
    glers
    -0.86
     ILCS
    -0.84
    atre
    -0.74
    aughtered
    -0.72
    kj
    -0.71
    vr
    -0.69
    aea
    -0.68
    dit
    -0.67
    iple
    -0.67
    UGE
    -0.66
    POSITIVE LOGITS
     stating
    1.85
     noting
    1.82
     saying
    1.70
     arguing
    1.62
     asserting
    1.62
     claiming
    1.54
     citing
    1.50
     mentioning
    1.50
     pointing
    1.49
     insisting
    1.48
    Activations Density 0.293%

    No Known Activations