Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9943
    Prev
    Next
    INDEX
    Explanations

    instances related to protest movements or actions, particularly strikes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "strike" and its various forms in contexts related to labor or military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opher
    -0.69
    ħĭ
    -0.68
    ophers
    -0.67
    Va
    -0.64
    hemy
    -0.64
    entric
    -0.63
    regon
    -0.63
    ivil
    -0.62
    ITY
    -0.61
    ŀ
    -0.61
    POSITIVE LOGITS
     strike
    1.00
    breakers
    0.89
     striking
    0.84
    force
    0.79
     struck
    0.79
     strikes
    0.78
    strike
    0.77
    deen
    0.74
    Strike
    0.73
     force
    0.73
    Activations Density 0.016%

    No Known Activations