© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19844
    Prev
    Next
    INDEX
    Explanations

    various programming language terms and syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    the pattern of closing parenthesis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     virtue
    -0.61
     Budd
    -0.60
     Carson
    -0.56
     ages
    -0.55
     thanks
    -0.54
     Sing
    -0.54
     signs
    -0.52
     measuring
    -0.52
     proportions
    -0.52
     bust
    -0.52
    POSITIVE LOGITS
    ))
    3.81
    )))
    3.47
    ))))
    3.32
    )).
    3.25
     ))
    3.15
    "))
    3.11
    )),
    3.08
     )))
    2.94
    ));
    2.93
    ])
    2.67
    Activations Density 0.011%

    No Known Activations