© 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. 2-RES-JB
    11. 12497
    Prev
    Next
    INDEX
    Explanations

    words related to disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rep" in various contexts related to reputation, representation, or reparations

    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
    glers
    -0.92
    ppo
    -0.83
    ERY
    -0.77
    BuyableInstoreAndOnline
    -0.77
     Abyss
    -0.74
     Cage
    -0.73
     Ducks
    -0.72
     Bruins
    -0.71
    ggle
    -0.69
    gers
    -0.68
    POSITIVE LOGITS
    utations
    1.28
    rint
    1.06
    arations
    1.03
    rieve
    1.00
    ainted
    0.99
    utation
    0.97
    rehens
    0.95
    onse
    0.95
    uted
    0.93
    ublic
    0.93
    Activations Density 0.010%

    No Known Activations