© 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. 7001
    Prev
    Next
    INDEX
    Explanations

    words related to clothing and accessories

    oai_token-act-pair · gpt-3.5-turbo

    specific segments of language related to food and consumption

    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
     Accountability
    -0.61
    ©¶æ¥µ
    -0.54
     Cheong
    -0.51
     gracious
    -0.50
     Pwr
    -0.49
     Jindal
    -0.49
     Parish
    -0.49
     Equity
    -0.49
     credibility
    -0.48
     Jav
    -0.47
    POSITIVE LOGITS
    ilib
    0.79
    omorph
    0.70
    acters
    0.70
    ids
    0.68
    ahs
    0.67
    ction
    0.66
    ption
    0.66
    uffs
    0.65
    plings
    0.65
    uration
    0.64
    Activations Density 0.375%

    No Known Activations