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. 7-RES-JB
    6. 22250
    Prev
    Next
    INDEX
    Explanations

    countries and political entities

    oai_token-act-pair · gpt-3.5-turbo

    entities related to political or social groups and their affiliations

    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
     Stam
    -0.64
    antha
    -0.62
    ËĪ
    -0.61
     Aval
    -0.60
     Loyal
    -0.60
     Lent
    -0.59
    _.
    -0.57
    ().
    -0.57
     ±
    -0.56
     Jah
    -0.56
    POSITIVE LOGITS
     alike
    1.78
     are
    1.07
     were
    1.06
     respectively
    0.98
     weren
    0.92
     aren
    0.92
     collide
    0.87
     have
    0.86
     remain
    0.85
     collided
    0.80
    Activations Density 0.382%

    No Known Activations