© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    French words and phrases

    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
    ãĤĭ
    -0.85
    vals
    -0.84
     Veter
    -0.82
    Vs
    -0.81
     vet
    -0.81
    姫
    -0.79
     Vietnam
    -0.77
     Vet
    -0.76
     Vale
    -0.75
     Versus
    -0.73
    POSITIVE LOGITS
    ipp
    1.06
    heng
    0.96
    oÄŁan
    0.95
    oul
    0.94
    odd
    0.88
    ke
    0.84
    kef
    0.83
    he
    0.82
     tong
    0.80
    ophen
    0.79
    Activations Density 0.319%

    No Known Activations