© 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. 6397
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict, war, and violence

    oai_token-act-pair · gpt-3.5-turbo

    commas and punctuation indicating pauses or transitions in 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
    ukong
    -0.73
    abouts
    -0.73
    tera
    -0.69
    ":"/
    -0.68
    ource
    -0.66
    Nonetheless
    -0.65
    utenant
    -0.64
    lance
    -0.64
    Availability
    -0.63
    azeera
    -0.63
    POSITIVE LOGITS
     culminating
    1.28
     transforming
    1.21
     hoping
    1.15
     creating
    1.13
     exposing
    1.12
     declaring
    1.12
     stripping
    1.11
     proclaiming
    1.11
     unveiling
    1.09
     handing
    1.09
    Activations Density 0.354%

    No Known Activations