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. 3-RES-JB
    6. 11864
    Prev
    Next
    INDEX
    Explanations

    terms related to alt-right movements

    oai_token-act-pair · gpt-3.5-turbo

    references to the alt-right or alternative political movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.80
    ecause
    -0.80
    loo
    -0.75
     Affect
    -0.72
    EEE
    -0.70
    interrupted
    -0.69
    bah
    -0.69
    LOCK
    -0.68
    cence
    -0.68
    OA
    -0.67
    POSITIVE LOGITS
    itud
    1.05
     alt
    1.04
    itudes
    1.00
    itude
    0.82
    itudinal
    0.80
    ogether
    0.79
     ascend
    0.78
    imeter
    0.78
    icter
    0.71
     altitude
    0.69
    Activations Density 0.007%

    No Known Activations