Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21724
    Prev
    Next
    INDEX
    Explanations

    Proper nouns related to individuals named George or Georg

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Georg" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    footed
    -0.83
    pled
    -0.72
    chief
    -0.66
    tsky
    -0.66
    ointed
    -0.63
     SEAL
    -0.63
     lodge
    -0.62
    FACE
    -0.61
     CSI
    -0.61
     marrow
    -0.60
    POSITIVE LOGITS
    iev
    1.14
    ians
    1.11
    opol
    1.03
    iana
    1.00
     Georg
    0.99
    Georg
    0.97
    eson
    0.90
    ophe
    0.88
    ieve
    0.86
    ues
    0.85
    Activations Density 0.017%

    No Known Activations