© 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. 1-RES-JB
    11. 2199
    Prev
    Next
    INDEX
    Explanations

    keywords related to the idea of "presence."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "presence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imb
    -0.77
    romy
    -0.71
    ETA
    -0.69
    sen
    -0.68
     externalToEVAOnly
    -0.68
    EStreamFrame
    -0.68
    bi
    -0.67
    DES
    -0.65
    YR
    -0.65
    rote
    -0.64
    POSITIVE LOGITS
     presence
    1.34
     Presence
    1.01
    enance
    0.89
    ngth
    0.88
    ailability
    0.73
    uality
    0.71
    =\"
    0.71
    lehem
    0.71
    iquette
    0.70
    idon
    0.69
    Activations Density 0.011%

    No Known Activations