© 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. 6417
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the name "Cole"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cole."

    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
    oppable
    -0.65
     recogn
    -0.62
    hots
    -0.59
     guiActiveUn
    -0.58
    CRIP
    -0.58
     Mehran
    -0.58
     Munich
    -0.58
    ocre
    -0.57
     loader
    -0.57
    oslav
    -0.57
    POSITIVE LOGITS
    tto
    1.21
    tti
    1.01
    brate
    0.90
    tta
    0.89
    voy
    0.88
    mons
    0.83
    bre
    0.82
    opter
    0.82
    lli
    0.82
    bourne
    0.81
    Activations Density 0.054%

    No Known Activations