© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 521
    Prev
    Next
    INDEX
    Explanations

    comparisons stating that two things are the same

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the same as."

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

    No Comments

    Negative Logits
    uca
    -0.70
    uci
    -0.63
    uto
    -0.62
    endale
    -0.62
    ulent
    -0.61
    ocy
    -0.60
    ople
    -0.59
    eker
    -0.59
    uld
    -0.59
    raq
    -0.58
    POSITIVE LOGITS
    ylum
    0.84
     regards
    0.80
    bestos
    0.67
     ours
    0.67
     Horton
    0.67
    ocial
    0.67
     usual
    0.66
    pects
    0.65
    pire
    0.64
     advertised
    0.63
    Activations Density 0.046%

    No Known Activations