© 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. 10-RES-JB
    11. 3173
    Prev
    Next
    INDEX
    Explanations

    links to images on Twitter

    oai_token-act-pair · gpt-3.5-turbo

    multiple occurrences of the period punctuation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunt
    -0.69
     disadvant
    -0.67
     conflic
    -0.66
     civilisation
    -0.65
     oun
    -0.65
     challeng
    -0.63
     Dane
    -0.63
     conclud
    -0.62
     nomine
    -0.62
     surprises
    -0.62
    POSITIVE LOGITS
    twitter
    1.86
    facebook
    1.08
    twitch
    1.08
    google
    1.05
    imgur
    1.02
    Twitter
    0.96
    youtube
    0.96
    wordpress
    0.95
    redd
    0.93
    php
    0.93
    Activations Density 0.015%

    No Known Activations