© 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. 2-RES-JB
    11. 19711
    Prev
    Next
    INDEX
    Explanations

    references to coverage related to insurance or media reporting

    oai_token-act-pair · gpt-3.5-turbo

    references to insurance or media coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rep
    -0.72
    raine
    -0.69
    ston
    -0.68
    rir
    -0.67
    warm
    -0.66
    tre
    -0.65
     arr
    -0.64
    eric
    -0.64
    ofi
    -0.64
     testament
    -0.63
    POSITIVE LOGITS
     Coverage
    1.36
     coverage
    1.33
    verage
    0.99
     COVER
    0.98
    oided
    0.88
    irtual
    0.87
    krit
    0.79
     cov
    0.79
     covering
    0.79
    illance
    0.75
    Activations Density 0.015%

    No Known Activations