Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21822
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to data and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arnaev
    -0.70
    SPONSORED
    -0.69
    ippery
    -0.66
     Allaah
    -0.65
     Clockwork
    -0.62
    uties
    -0.61
     Luther
    -0.61
     Quadro
    -0.61
    cham
    -0.61
    chev
    -0.59
    POSITIVE LOGITS
     )
    1.52
     ),
    1.51
     ):
    1.49
     ).
    1.45
     ,"
    1.45
     )]
    1.39
     );
    1.36
     ].
    1.36
     ."
    1.33
     ));
    1.32
    Activations Density 0.119%

    No Known Activations