© 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. 9-RES-JB
    11. 2257
    Prev
    Next
    INDEX
    Explanations

    numerical information related to year over year comparisons or growth rates

    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
     seiz
    -0.77
     Ruk
    -0.72
    ãĥķãĤ©
    -0.70
     Telesc
    -0.66
     Cipher
    -0.66
     Naked
    -0.66
     Scrib
    -0.64
    rypt
    -0.63
    ONT
    -0.63
     Razer
    -0.62
    POSITIVE LOGITS
    year
    1.00
     year
    0.93
    month
    0.87
    date
    0.86
     decade
    0.84
    Year
    0.79
    iversary
    0.78
     Year
    0.77
    years
    0.76
    instance
    0.75
    Activations Density 0.032%

    No Known Activations