© 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. 12056
    Prev
    Next
    INDEX
    Explanations

    email promotions and newsletters

    oai_token-act-pair · gpt-3.5-turbo
    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
    naire
    -0.59
    ilion
    -0.58
    bara
    -0.58
    _>
    -0.56
    llan
    -0.56
     largeDownload
    -0.54
    Rule
    -0.54
    auga
    -0.54
     disappearance
    -0.54
     brut
    -0.54
    POSITIVE LOGITS
     POLITICO
    0.79
    bleacher
    0.74
    ivably
    0.68
    independent
    0.67
     subscribing
    0.61
    ivered
    0.60
    taboola
    0.60
     Hels
    0.60
    rex
    0.59
    Dispatch
    0.59
    Activations Density 0.019%

    No Known Activations