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. 318
    Prev
    Next
    INDEX
    Explanations

    names or titles related to leadership positions, particularly those with "director" in them

    oai_token-act-pair · gpt-3.5-turbo

    the word "director" in various contexts

    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
     âĿ
    -0.69
    vier
    -0.66
    SI
    -0.66
    aches
    -0.65
    VAL
    -0.64
    achy
    -0.62
    umeric
    -0.62
    uine
    -0.61
    ols
    -0.60
    usable
    -0.60
    POSITIVE LOGITS
     director
    3.51
     Director
    2.71
    director
    2.71
    Director
    2.57
     directors
    2.54
     Directors
    1.90
     filmmaker
    1.81
     coordinator
    1.73
     chairman
    1.67
     manager
    1.67
    Activations Density 0.024%

    No Known Activations