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. 6302
    Prev
    Next
    INDEX
    Explanations

    mentions of close relationships or partnerships, especially involving activities related to crime or shared endeavors

    oai_token-act-pair · gpt-3.5-turbo

    references to partnerships or collaborations involving friends or companions

    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
    limits
    -0.69
    lems
    -0.64
    ynes
    -0.63
    lite
    -0.62
    fter
    -0.61
    :/
    -0.61
    ifact
    -0.60
     dictated
    -0.59
     gates
    -0.59
    cale
    -0.59
    POSITIVE LOGITS
    thood
    0.87
     whom
    0.86
    aukee
    0.81
    sharing
    0.71
    brother
    0.66
     Antioch
    0.66
    acas
    0.65
     BMC
    0.63
     IRC
    0.61
     Wales
    0.61
    Activations Density 0.397%

    No Known Activations