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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17502
    Prev
    Next
    INDEX
    Explanations

    people in service roles

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to service and support professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skirts
    -0.67
    aepernick
    -0.66
    jiang
    -0.65
    çīĪ
    -0.64
    ADD
    -0.64
     resurgence
    -0.64
     enduring
    -0.63
    ¥µ
    -0.63
    wikipedia
    -0.62
     headlines
    -0.62
    POSITIVE LOGITS
    esses
    1.12
     overseeing
    0.98
     supervisor
    0.97
    ess
    0.92
    who
    0.88
     who
    0.88
     oversee
    0.85
     superv
    0.85
     specializing
    0.84
     instructed
    0.84
    Activations Density 0.323%

    No Known Activations