© 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. 4-RES-JB
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    key ideas or points highlighted as "First" in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "First" indicating a sequence or enumeration

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

    No Comments

    Negative Logits
    sav
    -0.69
    ucl
    -0.64
    âĹ¼
    -0.63
    mbuds
    -0.63
    utic
    -0.63
     Gould
    -0.62
    maps
    -0.62
    ourge
    -0.62
    EXT
    -0.62
    ding
    -0.62
    POSITIVE LOGITS
     responders
    1.03
     blush
    0.81
     awa
    0.79
     baseman
    0.78
     glance
    0.78
     accuser
    0.77
     Listen
    0.76
     premise
    0.75
     impressions
    0.74
     Amendment
    0.74
    Activations Density 0.032%

    No Known Activations