© 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. 7645
    Prev
    Next
    INDEX
    Explanations

    requests or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or requests directed at the reader or audience

    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
     partic
    -0.58
    ement
    -0.57
     difficulty
    -0.55
     perm
    -0.52
     pains
    -0.51
    pole
    -0.51
     cod
    -0.51
    cknowled
    -0.50
     sensit
    -0.50
     derog
    -0.50
    POSITIVE LOGITS
     See
    0.69
    \/\/
    0.57
     Videos
    0.57
    "))
    0.56
    á½
    0.56
    img
    0.56
     Shap
    0.56
    rina
    0.55
    Interstitial
    0.55
    gdala
    0.54
    Activations Density 0.019%

    No Known Activations