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. 6312
    Prev
    Next
    INDEX
    Explanations

    mentions of conflicts, crises, and strong reactions in diverse contexts

    oai_token-act-pair · gpt-3.5-turbo
    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
    ocytes
    -0.82
    iple
    -0.71
    amera
    -0.69
    thren
    -0.68
    enth
    -0.67
    inately
    -0.66
    untarily
    -0.65
    emed
    -0.64
    gae
    -0.64
    imum
    -0.64
    POSITIVE LOGITS
     culminating
    1.41
     coupled
    1.39
     exacerbated
    1.26
     which
    1.20
     compounded
    1.07
     including
    1.05
     wherein
    1.04
     stemming
    1.04
     whereby
    1.02
     fueled
    1.02
    Activations Density 0.399%

    No Known Activations