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. 1-RES-JB
    6. 7777
    Prev
    Next
    INDEX
    Explanations

    mentions of the Kurdish Peshmerga fighters

    oai_token-act-pair · gpt-3.5-turbo

    references to the Peshmerga forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.96
     DRAG
    -0.84
    ership
    -0.80
     Butterfly
    -0.77
    IBLE
    -0.76
    iliary
    -0.75
    ered
    -0.69
    edded
    -0.68
     Sleeping
    -0.66
     Forbidden
    -0.65
    POSITIVE LOGITS
    merga
    1.78
     Pesh
    1.17
    awar
    1.16
    istani
    0.90
    marg
    0.89
    iman
    0.75
    bole
    0.73
    idates
    0.72
    inka
    0.72
    agin
    0.71
    Activations Density 0.007%

    No Known Activations