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. 10-RES-JB
    6. 7371
    Prev
    Next
    INDEX
    Explanations

    phrases related to ambiguity or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional states and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.68
    ario
    -0.64
    nexus
    -0.61
    nie
    -0.61
    athi
    -0.60
    arial
    -0.59
    hene
    -0.59
    nc
    -0.59
    ington
    -0.58
    glas
    -0.58
    POSITIVE LOGITS
    ined
    0.80
    usted
    0.77
    inately
    0.76
    ained
    0.75
    ighed
    0.74
    ivably
    0.73
    iguous
    0.73
    inated
    0.72
    oint
    0.69
    inating
    0.68
    Activations Density 0.059%

    No Known Activations