© 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. 1-RES-JB
    11. 20273
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense that signify control or influence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dominate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ft
    -0.75
    cknowled
    -0.72
    pt
    -0.72
    Mesh
    -0.68
    safety
    -0.68
    anger
    -0.66
    lev
    -0.63
    den
    -0.62
    aration
    -0.62
    bel
    -0.62
    POSITIVE LOGITS
     dominated
    1.09
     dominates
    1.07
     dominate
    1.01
     overshadowed
    0.85
    xual
    0.81
     dominating
    0.79
    daq
    0.78
     headlines
    0.77
     dominance
    0.73
     sweets
    0.72
    Activations Density 0.010%

    No Known Activations