© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23895
    Prev
    Next
    INDEX
    Explanations

    phrases related to scouting or scouts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scouting in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Torrent
    -0.71
     Pyr
    -0.70
    iac
    -0.66
    teness
    -0.66
    lihood
    -0.65
    pour
    -0.65
    tons
    -0.65
     catast
    -0.61
    ãĤ´ãĥ³
    -0.61
    ktop
    -0.60
    POSITIVE LOGITS
     scout
    1.00
     Scouting
    0.97
     troop
    0.92
     scouts
    0.89
     scouting
    0.87
     Scouts
    0.84
    lon
    0.83
     sergeant
    0.79
    masters
    0.79
    udo
    0.75
    Activations Density 0.048%

    No Known Activations