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. 1468
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles of works or products that have the word 'Original' in them

    oai_token-act-pair · gpt-3.5-turbo

    the term "Original" in relation to 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
    rooms
    -0.75
    aiman
    -0.72
    acht
    -0.70
    ucket
    -0.70
    wal
    -0.70
    athered
    -0.70
    risome
    -0.68
    attled
    -0.68
    oned
    -0.68
    walk
    -0.66
    POSITIVE LOGITS
     Poster
    0.91
    Filename
    0.89
    ity
    0.83
    istar
    0.72
     Answer
    0.71
     filename
    0.71
     Release
    0.70
    Original
    0.70
     Story
    0.69
    ITY
    0.69
    Activations Density 0.009%

    No Known Activations