© 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. 20214
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically with the surname "Phillips"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Phillips."

    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
    ERAL
    -0.76
    ctors
    -0.73
    fy
    -0.71
    gary
    -0.71
    Interstitial
    -0.70
    clud
    -0.70
    flow
    -0.70
    gha
    -0.68
    hibition
    -0.67
     quo
    -0.65
    POSITIVE LOGITS
     Lovecraft
    1.00
    ippi
    0.99
    ussen
    0.89
    atile
    0.89
    ions
    0.79
    sey
    0.77
    ioned
    0.76
    pie
    0.76
    ipher
    0.73
    hift
    0.72
    Activations Density 0.041%

    No Known Activations