© 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. 8-RES-JB
    11. 15015
    Prev
    Next
    INDEX
    Explanations

    business partnerships and collaborations

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words indicating partnerships or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.87
    imental
    -0.85
     equival
    -0.81
    ptoms
    -0.80
    numbered
    -0.78
     pend
    -0.75
    itri
    -0.75
    iated
    -0.74
    imester
    -0.71
     balance
    -0.71
    POSITIVE LOGITS
     partner
    0.87
     STATS
    0.86
     partners
    0.86
     Panasonic
    0.82
     Kinnikuman
    0.79
     collaborators
    0.78
     Tec
    0.78
     Habit
    0.78
     Geh
    0.77
     Bun
    0.76
    Activations Density 0.186%

    No Known Activations