© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3490
    Prev
    Next
    INDEX
    Explanations

    sequences with numbers related to lists or rankings

    oai_token-act-pair · gpt-3.5-turbo

    the concept of ranking or categorizing items, particularly in a competitive context

    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
     intrusive
    -0.69
    Detect
    -0.65
    schild
    -0.63
     impulse
    -0.62
    gerald
    -0.59
     Pamela
    -0.59
    Attorney
    -0.57
    uphem
    -0.57
    behavior
    -0.57
     Anon
    -0.56
    POSITIVE LOGITS
     tournaments
    1.39
     tournament
    1.39
     relegation
    1.31
     Championship
    1.29
     Tournament
    1.28
     finals
    1.28
     Championships
    1.28
     championships
    1.27
     Champions
    1.26
     Finals
    1.25
    Activations Density 1.080%

    No Known Activations