© 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. 8543
    Prev
    Next
    INDEX
    Explanations

    nouns related to actions or outcomes

    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
     congr
    -0.69
    etts
    -0.67
     thanked
    -0.63
    knit
    -0.62
     congratulated
    -0.61
     Roots
    -0.60
    erning
    -0.59
     Redd
    -0.57
     recognizes
    -0.56
    nect
    -0.56
    POSITIVE LOGITS
     incorrectly
    1.52
     inconsist
    1.50
     wrong
    1.45
     poorly
    1.41
     incorrect
    1.41
     inappropriately
    1.35
     improperly
    1.33
     unnecessarily
    1.30
     unsu
    1.29
     inaccurate
    1.29
    Activations Density 1.029%

    No Known Activations