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. 3-RES-JB
    6. 11756
    Prev
    Next
    INDEX
    Explanations

    instances where something is being done "properly."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "properly" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.79
    RY
    -0.70
    ————————
    -0.69
    _>
    -0.67
    oleon
    -0.67
    yi
    -0.67
    ————————————————
    -0.65
     spont
    -0.65
    tery
    -0.65
    ites
    -0.64
    POSITIVE LOGITS
     behaved
    0.94
     exting
    0.92
     fitted
    0.89
     formatted
    0.86
     aligned
    0.86
     equipped
    0.86
     initialized
    0.85
     segregated
    0.84
     positioned
    0.84
     suited
    0.83
    Activations Density 0.012%

    No Known Activations