© 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. 3-RES-JB
    11. 3469
    Prev
    Next
    INDEX
    Explanations

    the word "dom" regardless of its context

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "dominate."

    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
     Bulg
    -0.70
     Annotations
    -0.70
    Cause
    -0.70
    externalActionCode
    -0.65
     Braun
    -0.65
    displayText
    -0.64
     kHz
    -0.64
    âĢł
    -0.64
    keeper
    -0.64
    felt
    -0.62
    POSITIVE LOGITS
    inant
    1.24
    estic
    1.21
    inance
    1.20
    dom
    1.12
    ains
    1.01
    doms
    1.00
    ination
    0.98
    inal
    0.98
    inating
    0.97
    antis
    0.96
    Activations Density 0.009%

    No Known Activations