© 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. 10-RES-JB
    11. 10281
    Prev
    Next
    INDEX
    Explanations

    words related to household items and activities

    oai_token-act-pair · gpt-3.5-turbo

    lists and sequences of items or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hift
    -0.67
    orem
    -0.66
    keyes
    -0.66
    iciary
    -0.65
    kamp
    -0.60
    cedes
    -0.59
    cano
    -0.57
    tsky
    -0.57
    runs
    -0.57
    nels
    -0.57
    POSITIVE LOGITS
     etc
    1.71
    etc
    1.40
    whatever
    1.02
     whatever
    0.99
     and
    0.92
     even
    0.90
     blah
    0.87
    anything
    0.83
     et
    0.81
     maybe
    0.78
    Activations Density 0.163%

    No Known Activations