© 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. 7-RES-JB
    11. 22840
    Prev
    Next
    INDEX
    Explanations

    symbols denoting special characters and formatting

    oai_token-act-pair · gpt-3.5-turbo

    numeric or statistical data related to impactful events or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agre
    -0.81
     citiz
    -0.79
    abwe
    -0.77
     tradem
    -0.76
     veter
    -0.76
     redes
    -0.75
     advoc
    -0.75
    hement
    -0.73
     neighb
    -0.70
     sovere
    -0.70
    POSITIVE LOGITS
    Reviewed
    1.01
     largeDownload
    0.91
    LIN
    0.91
    ³³³
    0.89
    Instant
    0.84
    Associated
    0.84
    cery
    0.83
    Description
    0.82
    VERS
    0.81
    CHAPTER
    0.81
    Activations Density 0.043%

    No Known Activations