© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20194
    Prev
    Next
    INDEX
    Explanations

    references to job titles, specifically the word "supervisor"

    oai_token-act-pair · gpt-3.5-turbo

    the term "supervisor" and its variations

    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
    ting
    -0.84
    ilde
    -0.82
    ted
    -0.80
    auntlets
    -0.75
    enburg
    -0.74
    agra
    -0.73
    angular
    -0.71
    vor
    -0.69
    aval
    -0.68
    aston
    -0.67
    POSITIVE LOGITS
     supervisor
    1.32
     supervisors
    1.04
     Supervisor
    0.97
     overse
    0.82
    intendent
    0.72
    afety
    0.70
     confir
    0.68
     examiner
    0.67
    washer
    0.67
     dispatcher
    0.66
    Activations Density 0.008%

    No Known Activations