© 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. 0-RES-JB
    11. 8173
    Prev
    Next
    INDEX
    Explanations

    words related to the existence or occurrence of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "presence" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateurs
    -0.86
     miscar
    -0.63
    ibus
    -0.63
    wich
    -0.62
    utor
    -0.62
    hur
    -0.62
    emi
    -0.62
    ????
    -0.62
    ©¶æ
    -0.62
    YR
    -0.62
    POSITIVE LOGITS
     presence
    4.10
     Presence
    2.82
     absence
    2.06
     existence
    1.78
     arrival
    1.40
     footprint
    1.38
     involvement
    1.29
     proximity
    1.28
     foothold
    1.25
     dominance
    1.19
    Activations Density 0.009%

    No Known Activations