© 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. 10-RES-JB
    11. 11243
    Prev
    Next
    INDEX
    Explanations

    people involved in various situations or events, such as witnesses, workers, neighbors, and family members

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in a narrative or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consortium
    -0.81
     deserving
    -0.77
     decad
    -0.75
    iferation
    -0.73
     Submission
    -0.70
    uably
    -0.69
     winners
    -0.68
     Creator
    -0.68
     profitability
    -0.68
     Funding
    -0.67
    POSITIVE LOGITS
     witnessed
    1.40
     smelled
    1.30
     overheard
    1.30
     awoke
    1.28
     heard
    1.27
     woke
    1.26
     watched
    1.25
     alerted
    1.25
     saw
    1.22
     noticed
    1.19
    Activations Density 0.285%

    No Known Activations