© 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. 11-RES-JB
    11. 1583
    Prev
    Next
    INDEX
    Explanations

    mentions of strong opinions or views

    oai_token-act-pair · gpt-3.5-turbo

    statements or references related to significant events or noteworthy developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.92
    hua
    -0.76
    pill
    -0.75
    soDeliveryDate
    -0.72
    jen
    -0.72
    hap
    -0.71
    ynasty
    -0.71
    uchin
    -0.70
     Wolves
    -0.70
     suck
    -0.67
    POSITIVE LOGITS
     Ar
    2.44
    Ar
    2.12
     ar
    1.90
     AR
    1.80
     Ard
    1.45
     Archer
    1.45
     Arn
    1.36
     Kar
    1.28
    AR
    1.26
     Arche
    1.23
    Activations Density 0.294%

    No Known Activations