© 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. 23183
    Prev
    Next
    INDEX
    Explanations

    instances where someone was forced to do something against their will

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "forced to."

    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
     Done
    -0.68
    İ
    -0.67
     Laden
    -0.64
     Majority
    -0.63
    omen
    -0.62
    intent
    -0.61
    ouver
    -0.59
    pleasant
    -0.59
    calling
    -0.58
    /+
    -0.58
    POSITIVE LOGITS
     endure
    1.17
     concede
    1.12
     abandon
    1.11
     undergo
    1.10
     flee
    1.07
     rely
    1.06
     forfeit
    1.03
     confront
    1.02
     apologise
    1.01
     rethink
    0.99
    Activations Density 0.085%

    No Known Activations