© 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. 8-RES-JB
    11. 7249
    Prev
    Next
    INDEX
    Explanations

    words related to the term "refining" or words containing "ref"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ref" and its variations, indicating a focus on references or citations

    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
     Poles
    -0.66
    ################
    -0.64
     Horses
    -0.63
    MENTS
    -0.61
    ctica
    -0.60
     vulner
    -0.58
    worms
    -0.58
    CHO
    -0.57
     ending
    -0.57
    MENT
    -0.56
    POSITIVE LOGITS
    raction
    1.32
    ractive
    1.29
    actor
    1.27
    riger
    1.26
    eree
    1.23
    lection
    1.22
    erences
    1.22
    ocused
    1.18
    inement
    1.18
    lections
    1.18
    Activations Density 0.034%

    No Known Activations