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. 10-RES-JB
    6. 1943
    Prev
    Next
    INDEX
    Explanations

    information related to people named "Ari"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ari."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itionally
    -0.68
     Fargo
    -0.68
    FORMATION
    -0.67
     Beckham
    -0.66
     Dynam
    -0.65
    é¾
    -0.64
     Digest
    -0.62
     Newfoundland
    -0.62
     Sporting
    -0.61
     UDP
    -0.61
    POSITIVE LOGITS
    zon
    1.21
    zona
    1.07
    zeb
    1.04
    z
    1.03
    anna
    0.98
    zes
    0.97
    zos
    0.96
    jit
    0.96
    ana
    0.96
    ella
    0.92
    Activations Density 0.032%

    No Known Activations