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. 3276
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Pettitte."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named Pett or Pompe

    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
    VERTISEMENT
    -0.72
    lords
    -0.72
    ãĥ£
    -0.68
    âĸ¬âĸ¬
    -0.67
    LA
    -0.63
    âĸ¬
    -0.61
    lord
    -0.60
     rage
    -0.60
    dash
    -0.60
     grabbing
    -0.60
    POSITIVE LOGITS
    iment
    1.10
    iments
    1.09
    ername
    0.93
    ongyang
    0.92
     Pett
    0.92
    itone
    0.85
    acco
    0.84
     Canaveral
    0.82
     Pompe
    0.82
    ittees
    0.80
    Activations Density 0.027%

    No Known Activations