© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 2507
    Prev
    Next
    INDEX
    Explanations

    the article "a"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.79
    Edit
    -0.79
     presently
    -0.76
    eston
    -0.70
    hello
    -0.69
    Therefore
    -0.69
    enery
    -0.68
     âĢº
    -0.66
     hereby
    -0.66
    Entity
    -0.66
    POSITIVE LOGITS
     mistake
    1.04
     revelation
    1.01
     pivotal
    0.97
     surprise
    0.96
     precursor
    0.96
     breakthrough
    0.94
     catalyst
    0.94
     memorable
    0.91
     fateful
    0.89
     boon
    0.87
    Activations Density 0.171%

    No Known Activations