© 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 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. 10-RES-JB
    11. 6096
    Prev
    Next
    INDEX
    Explanations

    non-alphabetic characters or symbols, particularly those with repetition

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rooting
    -0.66
     veter
    -0.66
     right
    -0.65
     coupled
    -0.64
     signage
    -0.64
     appar
    -0.63
     partisans
    -0.63
    hement
    -0.62
     allied
    -0.62
     targets
    -0.62
    POSITIVE LOGITS
    Posted
    1.46
    RAW
    1.08
    ³³³
    1.06
    Synopsis
    1.05
    Loading
    1.04
    Reviewer
    0.98
    posted
    0.97
    Anonymous
    0.96
    Latest
    0.94
    Trivia
    0.93
    Activations Density 0.188%

    No Known Activations