© 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. 17454
    Prev
    Next
    INDEX
    Explanations

    unrelated incidents or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unrelated" 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
    lain
    -0.73
    ikan
    -0.71
    addafi
    -0.69
    aeper
    -0.69
    lance
    -0.68
    anism
    -0.68
    oÄŁ
    -0.67
     Crate
    -0.67
    unker
    -0.67
    tower
    -0.66
    POSITIVE LOGITS
     unrelated
    0.94
    hetical
    0.75
     thereto
    0.73
     trivial
    0.72
     twins
    0.68
    worldly
    0.65
    wise
    0.64
     wom
    0.64
     duplicate
    0.64
    worthy
    0.63
    Activations Density 0.010%

    No Known Activations