© 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. 2-RES-JB
    11. 535
    Prev
    Next
    INDEX
    Explanations

    the word "logic" or its derivatives

    oai_token-act-pair · gpt-4-turbo

    logical reasoning or arguments

    oai_token-act-pair · gpt-3.5-turbo

    references to logic and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eneg
    -0.72
    orks
    -0.72
     Volunte
    -0.72
    semble
    -0.71
    ometown
    -0.70
    Shar
    -0.68
    affer
    -0.68
    lain
    -0.66
    hold
    -0.63
     national
    -0.63
    POSITIVE LOGITS
     logic
    1.18
     Logic
    0.94
    matical
    0.87
    DragonMagazine
    0.82
    istically
    0.79
    matically
    0.79
     reasoning
    0.74
    istical
    0.73
     guiActiveUn
    0.73
    ãĤ¶
    0.72
    Activations Density 0.004%

    No Known Activations