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. 2-RES-JB
    6. 204
    Prev
    Next
    INDEX
    Explanations

    the last name "Lacey"

    oai_token-act-pair · gpt-3.5-turbo

    the sequence of characters "acey"

    oai_token-act-pair · gpt-4-turbo

    proper nouns, specifically names and references related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tarant
    -0.77
     martyr
    -0.77
     Abbas
    -0.73
     metic
    -0.71
    inal
    -0.70
     milit
    -0.69
     dreadful
    -0.69
     caliphate
    -0.69
     agon
    -0.67
     analges
    -0.67
    POSITIVE LOGITS
    lore
    0.89
    ãĤ½
    0.80
     Sparkle
    0.80
    theless
    0.79
     Weaver
    0.79
    anie
    0.79
     Emin
    0.79
    wagon
    0.79
     Crusher
    0.78
    heid
    0.76
    Activations Density 0.026%

    No Known Activations