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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8-RES-JB
    6. 1020
    Prev
    Next
    INDEX
    Explanations

    mentions of organized marches or protests

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "march" in various contexts related to protests or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terness
    -0.76
    eger
    -0.70
    omial
    -0.69
     bite
    -0.68
    nia
    -0.68
    folios
    -0.66
    vae
    -0.65
    lder
    -0.64
     forgiven
    -0.63
    IOR
    -0.63
    POSITIVE LOGITS
     marches
    0.92
     marching
    0.91
     march
    0.90
    antry
    0.86
     marched
    0.82
     toward
    0.81
    abouts
    0.81
    iage
    0.78
     towards
    0.78
    arity
    0.78
    Activations Density 0.024%

    No Known Activations