© 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. 11-RES-JB
    11. 9459
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is physically trapped or unable to move

    oai_token-act-pair · gpt-3.5-turbo

    instances of being "stuck" or "trapped" in various contexts

    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
     derived
    -0.68
     confir
    -0.61
    vernment
    -0.60
    iances
    -0.59
    1016
    -0.58
     Transparency
    -0.58
    urai
    -0.58
     dispel
    -0.58
    qua
    -0.58
    onse
    -0.58
    POSITIVE LOGITS
     between
    0.89
     somewhere
    0.88
     inside
    0.86
    locked
    0.86
     waiting
    0.86
     staring
    0.83
    between
    0.80
    ousel
    0.80
     upside
    0.79
     wondering
    0.78
    Activations Density 0.061%

    No Known Activations