© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 7392
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or titles

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the."

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

    No Comments

    Negative Logits
     thereof
    -0.90
     thereby
    -0.75
     respectively
    -0.75
    !.
    -0.72
    .''
    -0.69
     theirs
    -0.69
    .</
    -0.68
    ."
    -0.67
    ée
    -0.66
    tec
    -0.66
    POSITIVE LOGITS
    oret
    1.06
     latest
    1.05
     simplest
    0.99
    resa
    0.96
     largest
    0.94
     aforementioned
    0.94
    atre
    0.93
     biggest
    0.93
     same
    0.91
     toughest
    0.87
    Activations Density 1.061%

    No Known Activations