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. 14626
    Prev
    Next
    INDEX
    Explanations

    mentions of staff members or personnel in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "staff" 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
    ÑĮ
    -0.69
    âĵĺ
    -0.69
    imal
    -0.67
    NetMessage
    -0.65
     unpop
    -0.65
    aquin
    -0.65
     Downloads
    -0.64
     Tup
    -0.64
    ures
    -0.62
    abel
    -0.62
    POSITIVE LOGITS
     staff
    3.77
     Staff
    2.84
    staff
    2.66
    Staff
    2.62
     staffers
    2.41
     staffer
    2.11
     employees
    1.72
     personnel
    1.67
     staffing
    1.61
     faculty
    1.56
    Activations Density 0.015%

    No Known Activations