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. 6-RES-JB
    6. 18531
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, such as names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Charlie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.92
    nesota
    -0.88
    ahime
    -0.86
    haps
    -0.84
    yrim
    -0.81
    phasis
    -0.80
    dyl
    -0.79
    ersed
    -0.79
    senal
    -0.78
    ourced
    -0.78
    POSITIVE LOGITS
     Hebdo
    1.36
     Sheen
    1.08
     Manson
    0.95
     Cha
    0.93
     Brown
    0.88
     Cage
    0.87
     Daniels
    0.86
     Dent
    0.79
     Kaufman
    0.77
     Col
    0.77
    Activations Density 0.012%

    No Known Activations