© 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. 382
    Prev
    Next
    INDEX
    Explanations

    words related to extreme negative situations or conditions, such as monstrosity, atrocity, and deformities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative societal issues or injustices

    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
    olkien
    -0.78
    veland
    -0.76
    BOOK
    -0.73
    llan
    -0.71
    cham
    -0.68
    uden
    -0.67
     digitally
    -0.62
    book
    -0.62
    boarding
    -0.62
    houses
    -0.61
    POSITIVE LOGITS
    ity
    3.00
    ities
    2.22
    ITY
    1.63
    ité
    1.60
    ties
    1.46
    ation
    1.43
    ITIES
    1.42
    itous
    1.40
    ization
    1.37
    itarian
    1.34
    Activations Density 0.167%

    No Known Activations