© 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. 11-RES-JB
    11. 21998
    Prev
    Next
    INDEX
    Explanations

    questions related to possibility or capability

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hig
    -0.71
     Surveillance
    -0.67
    ahime
    -0.65
    ient
    -0.61
    ients
    -0.60
     Habit
    -0.59
    hib
    -0.59
    bris
    -0.57
    CI
    -0.57
     wherever
    -0.57
    POSITIVE LOGITS
     deny
    1.17
     accuse
    1.09
     ever
    0.98
     possibly
    0.96
     withstand
    0.96
     resist
    0.95
     EVER
    0.94
     refute
    0.92
     justify
    0.91
     conceive
    0.90
    Activations Density 0.112%

    No Known Activations