© 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. 0-RES-JB
    11. 9457
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals in leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Head."

    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
    PLA
    -0.72
    liga
    -0.71
    icity
    -0.69
     resil
    -0.68
    otin
    -0.63
     altru
    -0.62
     tyr
    -0.62
    vette
    -0.62
    krit
    -0.61
     cellul
    -0.60
    POSITIVE LOGITS
     Head
    3.75
    Head
    2.89
     Heads
    2.45
     head
    2.29
    head
    2.09
     HEAD
    1.97
     heads
    1.94
    HEAD
    1.84
    heads
    1.72
     Neck
    1.47
    Activations Density 0.012%

    No Known Activations