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. 7320
    Prev
    Next
    INDEX
    Explanations

    keywords related to BBC programs and interviews

    oai_token-act-pair · gpt-3.5-turbo

    references to BBC programming or related media

    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
     neighboring
    -0.77
     unfavorable
    -0.77
     realization
    -0.75
     finalized
    -0.72
     enrollment
    -0.71
     realized
    -0.71
     offensively
    -0.71
     favors
    -0.70
    colored
    -0.69
     Lamar
    -0.69
    POSITIVE LOGITS
     programme
    1.42
    BBC
    1.26
     programmes
    1.26
     Programme
    1.22
     BBC
    1.21
     presenter
    1.16
     Scotland
    1.11
    Scotland
    1.09
     ITV
    1.09
     Wales
    1.06
    Activations Density 0.213%

    No Known Activations