© 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. 10-RES-JB
    11. 24287
    Prev
    Next
    INDEX
    Explanations

    words related to legislation and government actions

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with numerical or measurement references

    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
     knockout
    -0.74
     mushroom
    -0.74
     reserve
    -0.73
     fancy
    -0.73
     endeavour
    -0.72
     coral
    -0.72
     civilisation
    -0.72
     spitting
    -0.72
     mint
    -0.71
     organising
    -0.71
    POSITIVE LOGITS
    âĢ
    1.97
    ADVERTISEMENT
    1.78
    Advertisement
    1.74
    âĸł
    1.72
    >>>
    1.69
    âĸº
    1.67
    âĹı
    1.65
    **
    1.57
    »
    1.57
    ***
    1.57
    Activations Density 0.446%

    No Known Activations