Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 62
    Prev
    Next
    INDEX
    Explanations

    the surname "Dugan" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the last name "Dug" and their mentions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the substring "Dug" within words

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.72
     Hurricanes
    -0.70
    nesota
    -0.68
     Kinnikuman
    -0.65
    SAY
    -0.65
     Oslo
    -0.63
     Proced
    -0.62
     comforting
    -0.61
     Viking
    -0.61
     Ronaldo
    -0.60
    POSITIVE LOGITS
     Dug
    1.31
    zag
    0.98
    glers
    0.91
    uid
    0.90
    dale
    0.86
    hess
    0.85
    ging
    0.85
    gar
    0.83
    gan
    0.82
    endum
    0.79
    Activations Density 0.006%

    No Known Activations