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. 0-RES-JB
    6. 7155
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jin"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bed
    -0.74
     amph
    -0.69
     Table
    -0.66
     PP
    -0.65
    MD
    -0.63
     Medicare
    -0.63
     Eucl
    -0.63
     EQU
    -0.62
     AAC
    -0.62
     McF
    -0.62
    POSITIVE LOGITS
    jin
    4.42
    jing
    1.56
     Jin
    1.31
    jit
    1.27
    kai
    1.27
    jong
    1.21
    ji
    1.19
    jah
    1.18
    jas
    1.18
    jo
    1.17
    Activations Density 0.012%

    No Known Activations