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. 13709
    Prev
    Next
    INDEX
    Explanations

    adjectives related to size and power

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "giant."

    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
    lest
    -0.83
    iring
    -0.78
    anwhile
    -0.78
    demand
    -0.77
    endment
    -0.75
    eligible
    -0.75
    etimes
    -0.74
    iency
    -0.73
    iggins
    -0.71
    tein
    -0.71
    POSITIVE LOGITS
     squid
    0.99
     mammoth
    0.87
     elephant
    0.87
     giant
    0.86
     gorilla
    0.83
     titan
    0.83
     iceberg
    0.80
     penis
    0.80
     monster
    0.79
     Slayer
    0.78
    Activations Density 0.010%

    No Known Activations