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. 10-RES-JB
    6. 13246
    Prev
    Next
    INDEX
    Explanations

    the name "Charlie" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.89
    rahim
    -0.86
    ĺħ
    -0.83
    ologically
    -0.76
    ahime
    -0.76
    atches
    -0.74
    inals
    -0.72
    inally
    -0.72
    ourced
    -0.71
    dyl
    -0.70
    POSITIVE LOGITS
     Hebdo
    1.46
     Sheen
    1.19
     Cha
    0.97
     Brown
    0.96
     Daniels
    0.93
     Manson
    0.87
    plin
    0.79
     Dent
    0.78
    anut
    0.77
     Schw
    0.76
    Activations Density 0.012%

    No Known Activations