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. 23765
    Prev
    Next
    INDEX
    Explanations

    references to specific sports teams or events, particularly the Kansas City Royals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and natural disaster terms

    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
    sth
    -0.96
    roth
    -0.94
    vest
    -0.88
    alogue
    -0.88
    atre
    -0.87
    aton
    -0.84
    elong
    -0.84
    vin
    -0.82
    ayers
    -0.82
    itude
    -0.81
    POSITIVE LOGITS
     Royals
    0.84
     annex
    0.82
     helic
    0.72
    angler
    0.71
     lockdown
    0.68
     mosqu
    0.68
     Cairo
    0.67
     shroud
    0.66
     tornado
    0.66
     tremend
    0.66
    Activations Density 0.031%

    No Known Activations