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. 0-RES-JB
    6. 3238
    Prev
    Next
    INDEX
    Explanations

    phrases related to introducing or beginning a new era or significant phase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transitions or introductions of new eras or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uffy
    -0.76
    ebin
    -0.70
    ierrez
    -0.70
     guessing
    -0.68
     disposition
    -0.67
     sore
    -0.67
    ouf
    -0.65
    Amount
    -0.65
    ross
    -0.65
     inconsistency
    -0.63
    POSITIVE LOGITS
     usher
    2.58
     herald
    2.23
     ushered
    2.06
     pioneer
    1.96
     inaug
    1.88
     pioneered
    1.81
     pioneering
    1.80
     paving
    1.77
     pioneers
    1.76
     groundbreaking
    1.68
    Activations Density 0.031%

    No Known Activations