© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13674
    Prev
    Next
    INDEX
    Explanations

    team-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to teams and group dynamics

    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
     Investor
    -0.70
     grocer
    -0.65
     prohibitions
    -0.62
     Tube
    -0.62
    grain
    -0.62
    trade
    -0.61
    ifle
    -0.60
     pollut
    -0.60
    vertis
    -0.59
    Tube
    -0.58
    POSITIVE LOGITS
     disbanded
    1.24
     comprised
    1.22
     consisted
    1.09
     consisting
    1.08
     assembled
    1.06
    members
    1.00
     consists
    1.00
     disband
    0.97
     composed
    0.96
    luaj
    0.92
    Activations Density 0.635%

    No Known Activations