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. 9-RES-JB
    6. 8358
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the rapper Lil Wayne

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names or terms associated with hip-hop culture and medical or geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.91
    awaru
    -0.86
    ractive
    -0.84
    racted
    -0.84
    urat
    -0.81
    lished
    -0.80
    ortion
    -0.80
    atted
    -0.79
    lain
    -0.77
    resses
    -0.77
    POSITIVE LOGITS
    bird
    0.80
     Birds
    0.79
     Nadu
    0.79
    iane
    0.79
     ANGEL
    0.78
     Pry
    0.71
    burgh
    0.69
     Angels
    0.67
    jen
    0.67
     Beans
    0.67
    Activations Density 0.134%

    No Known Activations