© 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. 4026
    Prev
    Next
    INDEX
    Explanations

    the name "Bouvet" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Bou

    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
    perse
    -0.66
    okin
    -0.65
    orph
    -0.65
    ulp
    -0.64
    bered
    -0.63
    ogens
    -0.61
    ORE
    -0.61
    aneously
    -0.60
    riors
    -0.60
    arty
    -0.60
    POSITIVE LOGITS
    yard
    0.79
    etooth
    0.77
    icas
    0.76
    ett
    0.74
    jee
    0.74
    iful
    0.74
    halla
    0.73
    eki
    0.72
    vertisement
    0.70
    maid
    0.69
    Activations Density 0.060%

    No Known Activations