© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 772
    Prev
    Next
    INDEX
    Explanations

    keywords related to the word "Word"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Word" and its 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
     Flavoring
    -0.75
    itant
    -0.72
    cffff
    -0.72
    etheus
    -0.70
    izo
    -0.69
    asio
    -0.67
    awaru
    -0.66
    NetMessage
    -0.65
    isner
    -0.64
    kens
    -0.64
    POSITIVE LOGITS
    press
    1.36
    sworth
    1.15
    play
    0.84
    Press
    0.83
     ptr
    0.83
     processor
    0.81
    mark
    0.81
    print
    0.81
    banks
    0.75
    edly
    0.74
    Activations Density 0.026%

    No Known Activations