© 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. 2334
    Prev
    Next
    INDEX
    Explanations

    mentions of news articles and interviews

    oai_token-act-pair · gpt-3.5-turbo

    references to published articles or writings

    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
    ãĤ©
    -0.69
     separ
    -0.67
     phyl
    -0.64
     fung
    -0.63
     helpers
    -0.63
    ETF
    -0.60
     mechanically
    -0.60
    ãĥīãĥ©
    -0.58
    rine
    -0.58
    ahime
    -0.58
    POSITIVE LOGITS
     Politico
    1.40
     Newsweek
    1.36
     TIME
    1.26
     BuzzFeed
    1.24
     POLITICO
    1.22
     Bloomberg
    1.22
     Salon
    1.20
     Vanity
    1.20
     Breitbart
    1.18
     HuffPost
    1.18
    Activations Density 0.242%

    No Known Activations