© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to names of places, people, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    parenthetical phrases or clauses

    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
     logged
    -0.72
    emort
    -0.70
     plugged
    -0.69
     accrued
    -0.67
     Loren
    -0.66
     manually
    -0.66
     DeV
    -0.66
     XT
    -0.66
     rigs
    -0.65
     clicks
    -0.65
    POSITIVE LOGITS
    meaning
    1.34
    literally
    1.26
    sic
    1.16
    God
    0.96
    Peace
    0.91
    çĦ
    0.90
    大
    0.89
    å¯
    0.89
    rough
    0.89
    Spanish
    0.88
    Activations Density 0.116%

    No Known Activations