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. 5144
    Prev
    Next
    INDEX
    Explanations

    functions or related terms within code snippets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of functions and their definitions in programming contexts

    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
    76561
    -0.83
     Hemp
    -0.73
    creen
    -0.72
     adul
    -0.72
    laus
    -0.71
     Robotics
    -0.69
    ±
    -0.67
     Sparkle
    -0.67
    bows
    -0.67
     Fever
    -0.67
    POSITIVE LOGITS
    matic
    0.86
    ality
    0.80
    ioned
    0.79
    alities
    0.79
    ctions
    0.77
    ivity
    0.77
     attm
    0.76
    abulary
    0.76
     functions
    0.75
    ional
    0.74
    Activations Density 0.015%

    No Known Activations