© 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. 0-RES-JB
    11. 6359
    Prev
    Next
    INDEX
    Explanations

    the suffix "-dom" in words

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "dom" and its variations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheaper
    -0.63
     beam
    -0.63
     Rapids
    -0.61
    ãĤ£
    -0.61
     lasers
    -0.60
     Blink
    -0.60
     Aurora
    -0.59
     gauge
    -0.59
     Repair
    -0.59
     quote
    -0.58
    POSITIVE LOGITS
    dom
    4.90
    doms
    3.44
    Dom
    2.29
    DOM
    2.10
     Dom
    1.51
     dom
    1.34
     DOM
    1.25
    edom
    1.20
    dit
    1.05
    hood
    1.03
    Activations Density 0.010%

    No Known Activations