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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 16085
    Prev
    Next
    INDEX
    Explanations

    verbs related to rapid change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating change or transformation in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     formerly
    -0.62
     extensively
    -0.61
     sorely
    -0.60
     Historically
    -0.60
     bluff
    -0.60
    initely
    -0.59
     traditionally
    -0.59
     inherently
    -0.59
     preserving
    -0.59
     constantly
    -0.58
    POSITIVE LOGITS
    ounters
    0.85
    ibaba
    0.73
    VALUE
    0.71
    argon
    0.71
    osen
    0.71
    mega
    0.70
    rier
    0.70
    ãĤ¼ãĤ¦ãĤ¹
    0.70
    ONEY
    0.70
    ependence
    0.69
    Activations Density 0.217%

    No Known Activations