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. 12792
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Akak"

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to individuals or entities, particularly in specific cultural or political contexts

    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
    ãĤ¡
    -0.66
     pint
    -0.65
    Ö¼
    -0.64
     Weasley
    -0.62
     Reaper
    -0.62
    drops
    -0.62
     alcohol
    -0.62
     Founders
    -0.61
     Pigs
    -0.60
     balloons
    -0.59
    POSITIVE LOGITS
    arak
    1.25
    unin
    1.18
    ota
    1.16
    umar
    1.12
    ansas
    1.09
    ihara
    1.03
    sha
    1.02
    unta
    0.98
    ushi
    0.98
    iri
    0.97
    Activations Density 0.021%

    No Known Activations