© 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. 3-RES-JB
    11. 10681
    Prev
    Next
    INDEX
    Explanations

    mentions of "board of directors"

    oai_token-act-pair · gpt-3.5-turbo

    references to boards of directors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Knox
    -0.75
    Bott
    -0.69
    Hur
    -0.68
     Hume
    -0.68
    ebook
    -0.66
    ADD
    -0.66
    FUL
    -0.65
    TN
    -0.65
    1000
    -0.64
    KEY
    -0.64
    POSITIVE LOGITS
    hips
    1.16
    hip
    1.09
    ervatives
    0.93
     directors
    0.88
    ettings
    0.84
    ervative
    0.84
    erv
    0.81
     trustees
    0.81
    redits
    0.80
    rats
    0.76
    Activations Density 0.015%

    No Known Activations