© 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. 7813
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of athletes and sports teams

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events or activities

    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
    âĵĺ
    -0.81
    ental
    -0.71
    "],"
    -0.69
    Submit
    -0.68
     Written
    -0.65
    Allah
    -0.63
    eros
    -0.62
     interven
    -0.62
    Cause
    -0.61
    anz
    -0.60
    POSITIVE LOGITS
    recent
    0.81
     resurg
    0.76
     sidel
    0.75
     replaced
    0.74
     controvers
    0.73
     inexper
    0.73
     resurrected
    0.72
     hindsight
    0.69
     bolstered
    0.68
     sandwic
    0.67
    Activations Density 0.780%

    No Known Activations