© 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. 0-RES-JB
    11. 3576
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where something or someone is missing or lacking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "absent" and its variations

    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
     Logo
    -0.69
    ests
    -0.65
    Market
    -0.62
    &
    -0.60
    bowl
    -0.58
    waters
    -0.58
     Life
    -0.57
     Dian
    -0.57
    ster
    -0.57
    json
    -0.57
    POSITIVE LOGITS
     absent
    3.93
     Absent
    2.18
     absence
    1.83
     absentee
    1.44
     nonexistent
    1.32
     lacking
    1.32
     missing
    1.29
     omitted
    1.27
     unavailable
    1.22
     omission
    1.21
    Activations Density 0.012%

    No Known Activations