© 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. 1-RES-JB
    11. 3555
    Prev
    Next
    INDEX
    Explanations

    comparative uses of the word "better" in the text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of improvement or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mad
    -0.71
    Py
    -0.68
    erity
    -0.67
    NH
    -0.66
    MIT
    -0.64
    idon
    -0.64
    Ar
    -0.63
    BRE
    -0.62
    psy
    -0.62
    TRY
    -0.61
    POSITIVE LOGITS
     suited
    0.97
     behaved
    0.89
     than
    0.84
     manag
    0.75
     payoff
    0.72
    seller
    0.70
     acquainted
    0.70
     tailor
    0.69
     behav
    0.68
     bet
    0.67
    Activations Density 0.032%

    No Known Activations