© 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. 9-RES-JB
    11. 15753
    Prev
    Next
    INDEX
    Explanations

    references to a particular code or abbreviation related to some entity named "Co"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Co" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.82
     IMAGES
    -0.73
     GOODMAN
    -0.68
    ICAN
    -0.67
     Halls
    -0.63
     Trou
    -0.63
     Yanuk
    -0.61
     Egyptians
    -0.60
    IONS
    -0.59
     RTX
    -0.58
    POSITIVE LOGITS
    aching
    1.19
    aches
    1.16
    herent
    1.13
    arse
    1.11
    ffee
    1.11
    oley
    1.11
    asters
    1.10
    verage
    1.10
    vers
    1.10
    efficients
    1.09
    Activations Density 0.029%

    No Known Activations