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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 23120
    Prev
    Next
    INDEX
    Explanations

    phrases related to executive and officer positions in organizations

    oai_token-act-pair · gpt-3.5-turbo

    job titles related to high-level corporate positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewitness
    -0.82
    otom
    -0.71
    leys
    -0.69
    Military
    -0.69
    haps
    -0.69
     Gladiator
    -0.68
    paren
    -0.66
    cend
    -0.64
     convict
    -0.63
    ramid
    -0.63
    POSITIVE LOGITS
     ABV
    0.77
     emer
    0.74
    âĢ¢âĢ¢
    0.73
    )=(
    0.71
     thereof
    0.70
    oft
    0.68
     Stacy
    0.68
     Steph
    0.68
    Initialized
    0.68
     Saur
    0.67
    Activations Density 0.091%

    No Known Activations