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. 22988
    Prev
    Next
    INDEX
    Explanations

    the word "supervisor" along with mentions of specific names or actions related to supervisors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to supervisory roles and positions

    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
    ãĥĨãĤ£
    -0.68
    phal
    -0.66
    lig
    -0.65
    liber
    -0.64
    bones
    -0.63
     Deals
    -0.62
     gib
    -0.61
     Dion
    -0.61
    Cele
    -0.61
    fal
    -0.60
    POSITIVE LOGITS
     supervisor
    3.75
     Supervisor
    3.45
     supervisors
    3.28
     superv
    1.71
    visors
    1.67
     supervision
    1.67
     dispatcher
    1.52
     superiors
    1.49
     superintendent
    1.46
     sergeant
    1.37
    Activations Density 0.011%

    No Known Activations