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. 3-RES-JB
    6. 13901
    Prev
    Next
    INDEX
    Explanations

    names of locations, especially in New York

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ..."
    -0.67
     EVs
    -0.53
     fame
    -0.52
    SPONSORED
    -0.51
     rigging
    -0.50
     naked
    -0.50
     precursor
    -0.50
     respectively
    -0.49
     steroids
    -0.47
     laying
    -0.47
    POSITIVE LOGITS
    theless
    0.70
     Profile
    0.68
    ashtra
    0.67
    udos
    0.65
    sonian
    0.62
    arius
    0.58
    ibliography
    0.57
    anyahu
    0.57
    yna
    0.56
    ':
    0.56
    Activations Density 0.702%

    No Known Activations