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. 0-RES-JB
    6. 16070
    Prev
    Next
    INDEX
    Explanations

    words related to human body parts, specifically ears

    oai_token-act-pair · gpt-3.5-turbo

    references to ears

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    java
    -0.74
    juven
    -0.65
    ifest
    -0.60
    raft
    -0.60
     Theft
    -0.59
     defended
    -0.58
    Ter
    -0.57
     Group
    -0.57
    vich
    -0.57
    saf
    -0.56
    POSITIVE LOGITS
     ears
    4.19
     ear
    2.21
     eyes
    1.73
     mouths
    1.62
     noses
    1.56
     headphones
    1.50
     tongues
    1.49
    Ear
    1.45
     horns
    1.45
     lips
    1.43
    Activations Density 0.020%

    No Known Activations