© 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. 11-RES-JB
    11. 2288
    Prev
    Next
    INDEX
    Explanations

    phrases related to synthesis or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and functions related to logical structures or processes

    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
     carbohyd
    -0.69
    reon
    -0.65
    elsius
    -0.64
     reluct
    -0.64
    isoft
    -0.62
     slic
    -0.61
    oken
    -0.60
    idal
    -0.59
    gement
    -0.59
    ratulations
    -0.58
    POSITIVE LOGITS
     .
    2.47
     ."
    1.97
     .)
    1.93
     ._
    1.66
     ".
    1.60
     '.
    1.55
     ).
    1.47
     ,"
    1.45
     ].
    1.39
     ,
    1.31
    Activations Density 0.317%

    No Known Activations