© 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. 24135
    Prev
    Next
    INDEX
    Explanations

    proper names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the name "Catherine" or similar variations

    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
    stru
    -0.74
    eat
    -0.73
    !/
    -0.71
    sword
    -0.71
    exec
    -0.69
    ending
    -0.68
    req
    -0.68
    ighters
    -0.67
    nesota
    -0.67
    eties
    -0.67
    POSITIVE LOGITS
    apy
    0.86
    issance
    0.81
    htaking
    0.80
    hew
    0.77
    nai
    0.76
     Byrne
    0.73
    Dialogue
    0.72
    lehem
    0.72
    loo
    0.72
     Byron
    0.72
    Activations Density 0.077%

    No Known Activations