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. 9-RES-JB
    6. 6546
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology

    oai_token-act-pair · gpt-3.5-turbo

    references to game mechanics and player actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enthusi
    -0.67
    cour
    -0.60
    Coming
    -0.57
    Tok
    -0.56
    Champ
    -0.56
    SIM
    -0.56
    Justice
    -0.56
    Wik
    -0.56
    Pic
    -0.55
    Apps
    -0.55
    POSITIVE LOGITS
    bernatorial
    0.71
    thora
    0.68
    ampire
    0.67
    ebus
    0.65
    olean
    0.64
    ļé
    0.63
    rican
    0.63
    onz
    0.61
    querade
    0.61
    onnaissance
    0.60
    Activations Density 0.617%

    No Known Activations