© 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. 6275
    Prev
    Next
    INDEX
    Explanations

    references to specific clothing items worn by individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe clothing or items being worn

    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
    borgh
    -0.73
    nery
    -0.71
    sburg
    -0.65
    alty
    -0.64
    itute
    -0.63
    Fer
    -0.62
    EMBER
    -0.62
    spawn
    -0.61
    Ess
    -0.60
    icult
    -0.60
    POSITIVE LOGITS
    stood
    1.39
    drawn
    1.19
    draw
    0.98
    holding
    0.89
     regard
    0.88
     impunity
    0.83
    standing
    0.78
     attachments
    0.76
     regards
    0.75
     bells
    0.74
    Activations Density 0.126%

    No Known Activations