© 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. 11-RES-JB
    11. 12236
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics or percentages

    oai_token-act-pair · gpt-3.5-turbo

    statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.78
     enthusi
    -0.76
    ModLoader
    -0.74
    Nitrome
    -0.69
     reluct
    -0.68
    aditional
    -0.66
     gobl
    -0.65
     tremend
    -0.64
     notor
    -0.63
     practition
    -0.61
    POSITIVE LOGITS
     cent
    1.63
    CENT
    1.02
    cent
    0.94
    secut
    0.91
    malink
    0.87
    secution
    0.86
     percentile
    0.84
     percent
    0.84
     Cent
    0.83
    missive
    0.83
    Activations Density 0.016%

    No Known Activations