© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18802
    Prev
    Next
    INDEX
    Explanations

    striking or labor-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to labor strikes and strike actions

    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
    iar
    -0.83
    ophers
    -0.80
    hemy
    -0.75
    ITIES
    -0.74
     Beir
    -0.73
    afort
    -0.73
    rehens
    -0.70
    ITY
    -0.69
    ħĭ
    -0.69
    opher
    -0.68
    POSITIVE LOGITS
    force
    1.05
    breakers
    1.04
     force
    0.88
    out
    0.84
    breaker
    0.84
     action
    0.77
    ters
    0.73
     zone
    0.73
    achi
    0.72
     stopp
    0.72
    Activations Density 0.034%

    No Known Activations