Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14342
    Prev
    Next
    INDEX
    Explanations

    references to scouting or scouts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scouting and recruitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pyr
    -0.75
    nces
    -0.66
    pour
    -0.65
    IST
    -0.64
    Torrent
    -0.64
    uctor
    -0.64
    death
    -0.64
    emon
    -0.63
    Act
    -0.63
    ĸļ
    -0.62
    POSITIVE LOGITS
     scout
    0.99
     scouts
    0.95
     scouting
    0.90
     Scouting
    0.84
    ota
    0.82
     sergeant
    0.78
    udo
    0.75
    sonian
    0.72
    oga
    0.72
    iors
    0.72
    Activations Density 0.016%

    No Known Activations