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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 340
    Prev
    Next
    INDEX
    Explanations

    mentions of hunger strikes

    oai_token-act-pair · gpt-3.5-turbo

    references to hunger strikes and the broader theme of hunger

    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
    VICE
    -0.77
    oral
    -0.76
     Offic
    -0.75
    afort
    -0.74
     Gentleman
    -0.70
     NRS
    -0.70
    oteric
    -0.70
     Noir
    -0.67
     Planetary
    -0.66
    Sphere
    -0.66
    POSITIVE LOGITS
     hunger
    1.10
     strikers
    1.03
    lust
    0.90
     cooker
    0.83
     striker
    0.83
     Hunger
    0.79
     strike
    0.77
    iless
    0.76
    itiveness
    0.76
     hungry
    0.75
    Activations Density 0.016%

    No Known Activations