© 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. 7-RES-JB
    11. 14386
    Prev
    Next
    INDEX
    Explanations

    specific dates or time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.65
     acronym
    -0.62
    ãĥ´
    -0.62
    ãĥĦ
    -0.61
    ographed
    -0.60
     gloss
    -0.58
     Shared
    -0.57
     echoed
    -0.57
     thumbs
    -0.56
     native
    -0.55
    POSITIVE LOGITS
     recess
    0.79
     onwards
    0.76
    cation
    0.75
    imental
    0.74
     onward
    0.71
    spection
    0.70
    imester
    0.69
    ties
    0.68
    idia
    0.68
    cture
    0.68
    Activations Density 0.182%

    No Known Activations