© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17230
    Prev
    Next
    INDEX
    Explanations

    instances of the character "Ļ"

    oai_token-act-pair · gpt-3.5-turbo

    the contraction "won't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Negro
    -0.60
     pyramid
    -0.55
     geo
    -0.55
     Gaul
    -0.54
     Tucson
    -0.54
     astronomers
    -0.53
     civilian
    -0.52
     Caf
    -0.52
     Kaf
    -0.51
     squirrel
    -0.51
    POSITIVE LOGITS
    iversary
    0.80
    ï¸ı
    0.77
    ember
    0.76
    tarian
    0.75
    emb
    0.73
    tre
    0.72
    $
    0.71
    sed
    0.70
    ç
    0.70
    udes
    0.68
    Activations Density 0.321%

    No Known Activations