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. 11-RES-JB
    6. 8015
    Prev
    Next
    INDEX
    Explanations

    mentions of global events or issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "world."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.96
    ippi
    -0.87
    imon
    -0.87
    sbm
    -0.78
    uckle
    -0.78
    omething
    -0.77
    ouri
    -0.77
    emale
    -0.73
     Mn
    -0.69
    pell
    -0.67
    POSITIVE LOGITS
     economy
    0.99
    liness
    0.91
     proletariat
    0.88
     premiere
    0.84
    ÃŃs
    0.82
    's
    0.82
     renowned
    0.81
     religions
    0.76
     renown
    0.72
     population
    0.72
    Activations Density 0.069%

    No Known Activations