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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 3442
    Prev
    Next
    INDEX
    Explanations

    words associated with being knowledgeable or skillful in a particular area, especially related to technology or business savvy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expertise and opportunism

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

    No Comments

    Negative Logits
    oration
    -0.70
    ãĤº
    -0.67
    ı
    -0.66
    arate
    -0.65
     Robots
    -0.63
    atern
    -0.62
    zai
    -0.62
     Schwarz
    -0.62
    aster
    -0.62
    ħ
    -0.61
    POSITIVE LOGITS
     savvy
    0.90
     opportun
    0.83
    ahime
    0.71
     charm
    0.71
    idious
    0.69
     deft
    0.68
     impecc
    0.68
    vier
    0.67
    flush
    0.67
    LOS
    0.66
    Activations Density 0.030%

    No Known Activations