© 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. 23695
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month and year

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sep" followed by numbers, likely indicating specific dates

    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
    culosis
    -0.99
     tuberculosis
    -0.78
     Archdemon
    -0.69
     Jackets
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
    anza
    -0.63
    Reviewer
    -0.63
     modem
    -0.62
     bearer
    -0.61
    ngth
    -0.60
    POSITIVE LOGITS
    arate
    1.27
    aration
    1.13
    ay
    0.95
    aret
    0.92
    ul
    0.87
    ared
    0.85
    ayed
    0.85
    arat
    0.81
    rees
    0.81
    ih
    0.81
    Activations Density 0.013%

    No Known Activations