© 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. 4-RES-JB
    11. 21988
    Prev
    Next
    INDEX
    Explanations

    references to the specific name "Coleman"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific athlete or player, particularly "Coleman."

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

    No Comments

    Negative Logits
    ymm
    -0.79
    hiro
    -0.76
    undo
    -0.73
    ocument
    -0.72
    oppable
    -0.71
    govtrack
    -0.69
    ãĥķãĤ©
    -0.68
    terior
    -0.68
    ODUCT
    -0.67
    ĻĤ
    -0.67
    POSITIVE LOGITS
     Coleman
    1.02
    voy
    0.75
     bleach
    0.74
     Watts
    0.74
     Carpenter
    0.73
    warm
    0.69
     Hawkins
    0.68
    herty
    0.68
     capsules
    0.67
     Burnett
    0.67
    Activations Density 0.007%

    No Known Activations