© 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. 9-RES-JB
    11. 4287
    Prev
    Next
    INDEX
    Explanations

    words with unusual characters or symbols in them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.74
    wards
    -0.69
     Commodore
    -0.68
    swick
    -0.66
     Sidd
    -0.66
    ITNESS
    -0.63
    washed
    -0.61
     Stard
    -0.59
     SOS
    -0.58
     gratification
    -0.58
    POSITIVE LOGITS
    ł
    1.45
    ¾
    1.42
    ĭ
    1.41
    Ĵ
    1.41
    ģ
    1.38
    ĵ
    1.37
    Į
    1.33
    ©
    1.30
    ı
    1.29
    Ī
    1.26
    Activations Density 0.023%

    No Known Activations