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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23361
    Prev
    Next
    INDEX
    Explanations

    phrases related to removing or eliminating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases about eliminating or getting rid of something

    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
    anwhile
    -0.69
     McDonnell
    -0.63
     Luxembourg
    -0.61
    enegger
    -0.59
    foreseen
    -0.58
     Kau
    -0.57
     Luxem
    -0.56
     Howell
    -0.55
     McKenzie
    -0.54
    Condition
    -0.52
    POSITIVE LOGITS
    icide
    0.87
     of
    0.81
    ged
    0.80
    ta
    0.80
    icides
    0.78
    estone
    0.77
    *=-
    0.74
    ges
    0.74
    uctions
    0.73
    eness
    0.73
    Activations Density 0.027%

    No Known Activations