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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 3237
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activism or protests

    oai_token-act-pair · gpt-3.5-turbo

    references to protests and political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pecul
    -0.60
     magnification
    -0.55
     partName
    -0.55
     Finder
    -0.55
     âĢº
    -0.54
     aback
    -0.54
     vantage
    -0.53
     anecd
    -0.52
    Adds
    -0.52
     versatility
    -0.51
    POSITIVE LOGITS
     amnesty
    0.68
     invading
    0.67
     legalized
    0.65
     homosexuality
    0.64
    assault
    0.62
     genocide
    0.61
    osate
    0.61
    hovah
    0.61
     AIDS
    0.60
    OTUS
    0.60
    Activations Density 1.643%

    No Known Activations