© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    the word "maybe" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the word "maybe."

    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
    cies
    -0.93
    arthed
    -0.92
    ourse
    -0.86
    lisher
    -0.80
    lete
    -0.80
    ezvous
    -0.79
    heny
    -0.77
    zeb
    -0.76
    ament
    -0.76
    orned
    -0.75
    POSITIVE LOGITS
     someday
    0.89
     maybe
    0.73
     Acer
    0.73
    ^^^^
    0.69
     sensing
    0.67
     SOME
    0.66
     subconscious
    0.65
     hint
    0.64
     messing
    0.63
     seriously
    0.63
    Activations Density 0.016%

    No Known Activations