© 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. 2575
    Prev
    Next
    INDEX
    Explanations

    specific time and date formats

    oai_token-act-pair · gpt-3.5-turbo

    specific time and date arrangements or events

    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
     Cosponsors
    -0.45
     Rohingya
    -0.43
    atcher
    -0.43
    allo
    -0.42
     resurg
    -0.41
     prosecutor
    -0.39
     Samar
    -0.39
     longtime
    -0.39
     watchdog
    -0.39
    erguson
    -0.38
    POSITIVE LOGITS
     increments
    0.59
    xxx
    0.59
     onwards
    0.57
    000000
    0.56
    $.
    0.55
    00
    0.55
     onward
    0.53
     cubic
    0.52
    cycles
    0.52
     hrs
    0.52
    Activations Density 0.598%

    No Known Activations