© 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. 6-RES-JB
    11. 14536
    Prev
    Next
    INDEX
    Explanations

    references to the name "Kurt" with high importance attached to instances where it's accompanied by the last name "Cobain"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kurt" and associated topics, particularly related to Kurt Cobain and Nirvana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cale
    -0.70
    Capital
    -0.69
    pring
    -0.68
    ersion
    -0.64
    grading
    -0.64
    advertisement
    -0.63
     systematic
    -0.63
     circ
    -0.61
     cyn
    -0.60
    maid
    -0.60
    POSITIVE LOGITS
    zman
    1.23
     Von
    1.11
     Angle
    0.91
     Kurt
    0.88
     Schwarz
    0.87
    inations
    0.85
    ãĥĦ
    0.84
     Hein
    0.83
     Andersen
    0.81
     Cob
    0.81
    Activations Density 0.018%

    No Known Activations