© 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. 8-RES-JB
    11. 17747
    Prev
    Next
    INDEX
    Explanations

    adjectives related to unusual or odd characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to unusual or odd phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igate
    -0.77
    agles
    -0.74
    vation
    -0.74
    bern
    -0.70
    inders
    -0.70
    apers
    -0.69
    tops
    -0.68
    mys
    -0.68
    glas
    -0.67
    cussion
    -0.67
    POSITIVE LOGITS
     occurrences
    0.98
     coincidence
    0.96
    ities
    0.93
    ness
    0.89
    worldly
    0.88
     coinc
    0.86
     assortment
    0.86
    ly
    0.85
     circumstances
    0.84
    pmwiki
    0.83
    Activations Density 0.063%

    No Known Activations