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

    Neuronpedia

    Jacobian LensNEW
    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. 4884
    Prev
    Next
    INDEX
    Explanations

    language related to programming, specifically focusing on code elements like files, functions, and implementations

    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
     prize
    -0.71
    rave
    -0.69
     acclaim
    -0.68
     Prize
    -0.67
    Tour
    -0.67
    politics
    -0.66
     Playboy
    -0.66
     prizes
    -0.65
     Carlton
    -0.64
     Newsp
    -0.63
    POSITIVE LOGITS
     initialized
    1.25
     deprecated
    1.22
     configured
    1.21
     implemented
    1.18
     useful
    1.17
    omorphic
    1.15
     handy
    1.14
     invoked
    1.13
     optimized
    1.13
     executable
    1.13
    Activations Density 0.154%

    No Known Activations