Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 16231
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mueller"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Robert Mueller and his legal investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pyr
    -0.86
     Zoro
    -0.74
     Columb
    -0.71
     Hawaiian
    -0.70
     Fiji
    -0.67
     Barbarian
    -0.67
    points
    -0.67
     Syri
    -0.66
     Samurai
    -0.66
    UX
    -0.64
    POSITIVE LOGITS
     Mueller
    0.99
     Probe
    0.89
     investigation
    0.83
    angelo
    0.82
    ueller
    0.82
     indict
    0.81
     investigations
    0.80
    owitz
    0.79
     investigating
    0.79
     probe
    0.78
    Activations Density 0.041%

    No Known Activations