© 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. 3-RES-JB
    11. 17676
    Prev
    Next
    INDEX
    Explanations

    terms related to logical reasoning or logic-oriented concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to logic in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Volunte
    -0.76
    ometown
    -0.71
    affer
    -0.70
    eneg
    -0.69
    lain
    -0.67
    orks
    -0.66
    emale
    -0.65
    Shar
    -0.64
    semble
    -0.64
    arers
    -0.64
    POSITIVE LOGITS
     logic
    1.11
     Logic
    0.91
    matical
    0.87
    istically
    0.75
    istical
    0.75
     puzzles
    0.74
     underpin
    0.74
    matically
    0.72
    inery
    0.72
    ical
    0.72
    Activations Density 0.006%

    No Known Activations