© 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. 21533
    Prev
    Next
    INDEX
    Explanations

    words related to negative societal issues and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to consequences and failures in various societal contexts

    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
     Released
    -0.58
     Lov
    -0.57
    sf
    -0.57
    artney
    -0.57
     Seasons
    -0.57
     Miles
    -0.55
     Goo
    -0.55
     Speedway
    -0.55
     Suns
    -0.54
    arthed
    -0.54
    POSITIVE LOGITS
    !.
    0.78
     fools
    0.77
    .—
    0.75
    !:
    0.74
    .–
    0.74
     whereby
    0.74
     whenever
    0.74
     insofar
    0.74
    âĢ
    0.73
     triv
    0.73
    Activations Density 0.361%

    No Known Activations