© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    images or visual representations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical information in the format 'number/number'

    oai_token-act-pair · gpt-3.5-turbo
    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
     Faw
    -0.63
     Wasserman
    -0.62
     Beir
    -0.59
    kson
    -0.56
     orchestr
    -0.56
    ework
    -0.55
     Alv
    -0.55
    itative
    -0.54
     Manson
    -0.53
    bats
    -0.53
    POSITIVE LOGITS
    ËĪ
    1.00
    Photos
    0.76
    Film
    0.75
    AUT
    0.70
    wcsstore
    0.68
    img
    0.68
    Courtesy
    0.68
    ĻĤ
    0.67
    ¼
    0.66
    irin
    0.66
    Activations Density 0.009%

    No Known Activations