© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12385
    Prev
    Next
    INDEX
    Explanations

    words related to interacting with content such as commenting, sharing, or providing feedback

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and expressions that encourage audience engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acute
    -0.85
     precip
    -0.82
     dismant
    -0.78
     displacement
    -0.77
    quartered
    -0.75
     tremend
    -0.74
     inaccur
    -0.72
     cumbers
    -0.72
     systematic
    -0.72
     deficient
    -0.72
    POSITIVE LOGITS
     ðŁĻĤ
    1.45
     :)
    1.43
     Lastly
    1.41
     Thanks
    1.39
     ;)
    1.36
     Enjoy
    1.35
     Until
    1.31
     Also
    1.30
    <|endoftext|>
    1.29
     :-)
    1.29
    Activations Density 0.207%

    No Known Activations