© 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. 17824
    Prev
    Next
    INDEX
    Explanations

    words containing the prefix 'und' combined with a following root word

    oai_token-act-pair · gpt-3.5-turbo

    words related to undressing or lack of clothing

    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
    ppo
    -0.73
    tsky
    -0.71
    zzo
    -0.69
    auga
    -0.68
    姫
    -0.67
    pheus
    -0.66
    anwhile
    -0.65
    gdala
    -0.64
    azines
    -0.64
    ongyang
    -0.64
    POSITIVE LOGITS
    etermined
    1.14
    aunted
    1.09
    oubt
    1.06
    iscovered
    1.03
    irect
    1.02
    ploy
    1.01
    epend
    1.00
    ried
    0.97
    efined
    0.95
    oubtedly
    0.93
    Activations Density 0.021%

    No Known Activations