Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4555
    Prev
    Next
    INDEX
    Explanations

    words related to facial hair and containers

    oai_token-act-pair · gpt-3.5-turbo

    references to physical characteristics or descriptors, particularly relating to beards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttes
    -0.72
     Mansion
    -0.72
    velt
    -0.71
     TMZ
    -0.71
     Vanity
    -0.64
     Byrd
    -0.64
    adelphia
    -0.63
    Ħ¢
    -0.62
    TM
    -0.61
     receiver
    -0.61
    POSITIVE LOGITS
     bearded
    2.00
     jug
    1.06
    ardless
    0.82
     ding
    0.69
    irez
    0.68
     scept
    0.66
    Austral
    0.66
    rael
    0.65
    IENT
    0.64
    between
    0.61
    Activations Density 0.007%

    No Known Activations