© 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. 22256
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences referring to a contrasting group or entity labeled as "everyone else."

    oai_token-act-pair · gpt-3.5-turbo

    references to societal perspectives or collective sentiments

    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
    rogram
    -0.72
    essee
    -0.69
    itor
    -0.66
    atre
    -0.66
    statement
    -0.63
    ppel
    -0.61
    umerable
    -0.61
    forestation
    -0.61
    rought
    -0.61
    ukong
    -0.59
    POSITIVE LOGITS
    worldly
    0.93
     except
    0.82
     alike
    0.73
     else
    0.67
     foss
    0.67
     nodd
    0.66
     revolves
    0.65
     imaginable
    0.64
    iah
    0.64
     mattered
    0.63
    Activations Density 0.034%

    No Known Activations