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. 8-RES-JB
    6. 19121
    Prev
    Next
    INDEX
    Explanations

    references to the body part "shoulder"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "shoulder."

    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
    yrinth
    -0.99
    eer
    -0.92
    eers
    -0.85
    esis
    -0.84
    inction
    -0.82
    antis
    -0.78
    ktop
    -0.78
    icative
    -0.77
    nom
    -0.73
    leon
    -0.73
    POSITIVE LOGITS
     blades
    1.13
     shoulder
    0.95
    bone
    0.92
     blade
    0.87
     shrug
    0.87
     straps
    0.85
     lobe
    0.81
     strap
    0.79
    bones
    0.78
    pless
    0.78
    Activations Density 0.030%

    No Known Activations