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. 0-RES-JB
    6. 705
    Prev
    Next
    INDEX
    Explanations

    the name "Ben Bernanke", specifically highlighting mentions of his name with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, likely a public figure or official

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.70
     Jol
    -0.69
     video
    -0.69
     division
    -0.68
     Vic
    -0.65
     Mill
    -0.65
     Str
    -0.65
     divided
    -0.65
     Cond
    -0.63
     conversions
    -0.63
    POSITIVE LOGITS
    anke
    5.02
    ellen
    1.37
    anamo
    1.16
    ubis
    1.16
    maxwell
    1.14
    uckland
    1.14
     Krugman
    1.11
    omsky
    1.09
    ructose
    1.06
    Reviewer
    1.05
    Activations Density 0.023%

    No Known Activations