© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7084
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    oai_token-act-pair · gpt-3.5-turbo

    dates and scheduling information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.88
    ibles
    -0.82
    hol
    -0.80
    och
    -0.77
    ios
    -0.76
    Hol
    -0.76
    Snow
    -0.75
     Gol
    -0.73
    ible
    -0.69
    NH
    -0.69
    POSITIVE LOGITS
     March
    1.61
     April
    1.50
    March
    1.48
    April
    1.36
     Marqu
    1.14
     February
    1.05
     marqu
    1.02
     march
    1.02
    Mar
    1.02
     Mar
    0.97
    Activations Density 0.161%

    No Known Activations