© 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. 17887
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "There" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "There"

    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
     CJ
    -0.83
     pound
    -0.74
     ±
    -0.72
     actionGroup
    -0.72
     micro
    -0.64
     +/-
    -0.63
     cum
    -0.62
     PG
    -0.61
     franc
    -0.61
     favour
    -0.61
    POSITIVE LOGITS
    abouts
    1.39
    upon
    1.03
    ntil
    0.92
    ngth
    0.88
    ilst
    0.85
    fore
    0.82
    after
    0.80
    olkien
    0.79
    ket
    0.78
     fortun
    0.77
    Activations Density 0.112%

    No Known Activations