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. 1-RES-JB
    6. 1678
    Prev
    Next
    INDEX
    Explanations

    titles or positions with the word "associate."

    oai_token-act-pair · gpt-3.5-turbo

    the term "associate" and its related context in academic or professional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stakes
    -0.76
    Politics
    -0.72
    Pet
    -0.72
    atever
    -0.69
    morrow
    -0.67
    ovies
    -0.66
    enty
    -0.66
    etheus
    -0.65
    cale
    -0.65
    depth
    -0.64
    POSITIVE LOGITS
     associate
    1.34
    ociate
    1.12
     associates
    0.91
     dean
    0.85
     associations
    0.80
    uate
    0.79
     Associates
    0.76
    iate
    0.75
    hesis
    0.73
     professor
    0.71
    Activations Density 0.007%

    No Known Activations