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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3010
    Prev
    Next
    INDEX
    Explanations

    phrases related to social movements

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Black Lives Matter" movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.84
    othy
    -0.72
    eatures
    -0.71
    oyal
    -0.70
    hiba
    -0.70
    Gi
    -0.68
    Wil
    -0.67
    ccording
    -0.67
    ãĥ³ãĤ¸
    -0.67
    bp
    -0.67
    POSITIVE LOGITS
     movement
    0.84
     protesters
    0.83
     protestors
    0.81
     Caucus
    0.80
     activists
    0.79
     protests
    0.79
     Movement
    0.78
     Protesters
    0.77
     Liberation
    0.76
    ovich
    0.76
    Activations Density 0.013%

    No Known Activations