© 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. 3-RES-JB
    11. 8198
    Prev
    Next
    INDEX
    Explanations

    the phrase "en masse"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "masse"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izoph
    -0.67
    Trend
    -0.65
    Ô
    -0.61
     Sisters
    -0.61
    nings
    -0.60
    nder
    -0.60
    INTON
    -0.59
    shield
    -0.59
     unanswered
    -0.59
     Ender
    -0.58
    POSITIVE LOGITS
     masse
    1.05
    chnology
    0.84
    aths
    0.82
    uary
    0.74
    ographed
    0.73
    ploy
    0.71
     proport
    0.71
    ume
    0.71
    visor
    0.70
    enaries
    0.70
    Activations Density 0.008%

    No Known Activations