© 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. 11-RES-JB
    11. 9490
    Prev
    Next
    INDEX
    Explanations

    timestamps or specific formats typically found in computer code

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and timestamps

    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
     Chambers
    -0.66
     fres
    -0.65
     Sant
    -0.64
    hett
    -0.62
     outright
    -0.61
     Jude
    -0.60
    ationally
    -0.60
     Pratt
    -0.58
     Rooney
    -0.58
     back
    -0.58
    POSITIVE LOGITS
    hover
    1.30
    YES
    1.04
    println
    0.96
    latest
    0.94
    4000
    0.93
    visible
    0.92
    param
    0.91
    none
    0.90
    memory
    0.90
    before
    0.90
    Activations Density 0.083%

    No Known Activations