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. 8014
    Prev
    Next
    INDEX
    Explanations

    references to Breitbart News and related individuals, such as Steve Bannon, in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news outlet Breitbart and related personnel

    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
    ktop
    -0.84
    atically
    -0.82
    hare
    -0.77
    mble
    -0.76
    iple
    -0.75
    wcsstore
    -0.73
    liness
    -0.70
    played
    -0.68
    awks
    -0.68
     captcha
    -0.68
    POSITIVE LOGITS
     News
    1.12
    NEWS
    0.96
    News
    0.96
    itbart
    0.93
     Breitbart
    0.82
     London
    0.81
    Daily
    0.79
     Tech
    0.78
    news
    0.77
     Texas
    0.77
    Activations Density 0.040%

    No Known Activations