© 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. 4204
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that include the word "Falco"

    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
    sburgh
    -0.67
     Leilan
    -0.63
    dress
    -0.62
    LESS
    -0.59
    ODUCT
    -0.59
     Borders
    -0.58
     Waste
    -0.57
     fabricated
    -0.57
     stiffness
    -0.56
     Boh
    -0.56
    POSITIVE LOGITS
    ters
    1.05
    tering
    1.04
    tered
    0.97
    quet
    0.97
    cone
    0.97
    ts
    0.88
    stad
    0.87
    quer
    0.86
    ter
    0.85
    ting
    0.84
    Activations Density 0.079%

    No Known Activations