© 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. 0-RES-JB
    11. 13034
    Prev
    Next
    INDEX
    Explanations

    specific symbols followed by a colon

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses

    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
     honey
    -0.48
     lad
    -0.47
     guiName
    -0.46
     hell
    -0.45
     arrangements
    -0.45
     heck
    -0.44
     baggage
    -0.42
     goodwill
    -0.42
     turkey
    -0.40
     haw
    -0.40
    POSITIVE LOGITS
    ):
    3.68
    .):
    3.13
     ):
    2.75
    ]:
    2.51
    )?
    1.99
    )—
    1.85
    )=
    1.79
    )!
    1.72
    )-
    1.66
    )--
    1.66
    Activations Density 0.014%

    No Known Activations