Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 2153
    Prev
    Next
    INDEX
    Explanations

    names, specifically "Naw", "Lochner", "Donna", and "Mush" in the text

    oai_token-act-pair · gpt-3.5-turbo

    repetition of the name "Naw" and references related to individuals named "Donna"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inquis
    -0.73
    NetMessage
    -0.69
     Cerberus
    -0.69
    ocaust
    -0.69
     Vampire
    -0.68
    chnology
    -0.64
    furt
    -0.63
     Edison
    -0.62
     Wonderland
    -0.61
    andals
    -0.59
    POSITIVE LOGITS
     Naw
    1.10
    rock
    0.94
    cks
    0.83
    uth
    0.82
    arak
    0.81
    abis
    0.81
    ay
    0.75
    awi
    0.75
    uddin
    0.75
    lette
    0.75
    Activations Density 0.012%

    No Known Activations