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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 2375
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis and scientific research

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data analysis and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    oret
    -0.60
    earchers
    -0.60
     concess
    -0.52
     corrid
    -0.50
     Eagles
    -0.49
     glim
    -0.48
    atchewan
    -0.46
     sear
    -0.46
     Somers
    -0.45
     subtle
    -0.45
    POSITIVE LOGITS
    )).
    1.67
    ]).
    1.46
    )))
    1.37
    ))))
    1.33
    ))
    1.31
    )?
    1.28
    )),
    1.24
     )))
    1.18
    ?).
    1.18
    ));
    1.17
    Activations Density 1.327%

    No Known Activations