© 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. 6517
    Prev
    Next
    INDEX
    Explanations

    facts or information within a news or article context

    oai_token-act-pair · gpt-3.5-turbo

    statements about news or investigative reports

    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
    sonian
    -0.57
    forth
    -0.56
    enhagen
    -0.56
    peria
    -0.55
    abee
    -0.55
    ufact
    -0.55
    Sham
    -0.53
    aic
    -0.52
    abad
    -0.50
    aved
    -0.50
    POSITIVE LOGITS
    esters
    0.67
    ½
    0.58
     ingred
    0.56
     annotation
    0.54
    osen
    0.54
    ortunately
    0.52
    ples
    0.52
    lean
    0.51
    launch
    0.51
     Cosponsors
    0.51
    Activations Density 0.242%

    No Known Activations