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. 12178
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people and organizations, particularly focusing on Ashton and paraplegic references

    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
    gments
    -0.87
    gers
    -0.85
    asures
    -0.82
     Gleaming
    -0.81
    INAL
    -0.80
    ãĤ´ãĥ³
    -0.77
    opoly
    -0.76
    reditary
    -0.75
    arcity
    -0.75
    oliberal
    -0.75
    POSITIVE LOGITS
     Ashton
    0.90
    bury
    0.78
     Elves
    0.76
     BM
    0.74
     Hort
    0.74
     Bulldogs
    0.72
     parap
    0.71
     BMC
    0.68
     Crusher
    0.66
     height
    0.66
    Activations Density 0.028%

    No Known Activations