© 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. 9-RES-JB
    11. 16745
    Prev
    Next
    INDEX
    Explanations

    statements of explanation or reason

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing certainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azon
    -0.62
     cann
    -0.60
    rams
    -0.60
    dule
    -0.59
     administer
    -0.59
     administering
    -0.58
    iless
    -0.57
     ultras
    -0.57
     packets
    -0.57
     TAMADRA
    -0.56
    POSITIVE LOGITS
     evidenced
    0.96
     exacerbated
    0.91
    Especially
    0.86
     worrisome
    0.85
    ummer
    0.85
     understandable
    0.84
     unsur
    0.83
     unfortunate
    0.82
     reflected
    0.82
     compounded
    0.82
    Activations Density 0.460%

    No Known Activations