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. 10-RES-JB
    6. 18292
    Prev
    Next
    INDEX
    Explanations

    questions related to the location or existence of a particular thing

    oai_token-act-pair · gpt-3.5-turbo

    questions or statements expressing a sense of absence or inquiry about location

    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
    arios
    -0.78
    iator
    -0.73
    cture
    -0.70
    iors
    -0.69
    CHO
    -0.68
    naires
    -0.67
    erenn
    -0.67
    ispers
    -0.67
    usk
    -0.66
    igmatic
    -0.64
    POSITIVE LOGITS
     Wald
    0.84
     money
    0.77
     inspiration
    0.75
     Ãľ
    0.75
     funds
    0.69
     outrage
    0.67
     Carmen
    0.63
     allegiance
    0.62
     accountability
    0.62
     happiest
    0.62
    Activations Density 0.054%

    No Known Activations