© 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. 15623
    Prev
    Next
    INDEX
    Explanations

    mentions of interactions with a specific group of people, such as colleagues or associates

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people, particularly those labeled as "fellow."

    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
    uilt
    -0.69
     livest
    -0.62
    _-
    -0.61
     Sue
    -0.60
    creen
    -0.60
    ussy
    -0.60
    âĵĺ
    -0.59
    anwhile
    -0.59
    onics
    -0.59
    itton
    -0.59
    POSITIVE LOGITS
     traveler
    1.22
     travelers
    1.17
     travellers
    1.06
     strugg
    1.05
    worldly
    1.01
     traveller
    0.95
     classmates
    0.92
    workers
    0.79
    worker
    0.79
     inmate
    0.78
    Activations Density 0.071%

    No Known Activations