© 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. 11-RES-JB
    11. 7436
    Prev
    Next
    INDEX
    Explanations

    URLs within the text

    oai_token-act-pair · gpt-3.5-turbo

    HTML attributes related to links and references

    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
     Shake
    -0.76
     Bang
    -0.74
     MFT
    -0.71
     Aires
    -0.70
     Generation
    -0.68
     Faw
    -0.67
     Chambers
    -0.66
     Budd
    -0.66
     NX
    -0.65
     equivalents
    -0.65
    POSITIVE LOGITS
    https
    1.55
    http
    1.46
    javascript
    1.42
    <?
    1.22
    //
    1.22
    styles
    1.15
    BuyableInstoreAndOnline
    1.12
    std
    1.10
    ../
    1.10
    {{
    1.08
    Activations Density 0.018%

    No Known Activations