© 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. 17975
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values separated by hyphens

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or numerical sequences

    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
    Enough
    -0.74
     Pigs
    -0.73
    HS
    -0.72
    Motor
    -0.71
    Channel
    -0.70
    Tags
    -0.70
    ================================================================
    -0.68
    TPS
    -0.66
    Specific
    -0.66
    INC
    -0.65
    POSITIVE LOGITS
    bryce
    0.66
     acad
    0.62
    abe
    0.60
     discovering
    0.59
     vulner
    0.57
     persu
    0.56
    gery
    0.56
     vil
    0.56
     hob
    0.56
     complying
    0.56
    Activations Density 0.058%

    No Known Activations