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. 20535
    Prev
    Next
    INDEX
    Explanations

    the name "Ty"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ty"

    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
    Ń·
    -0.85
    manship
    -0.82
    UME
    -0.79
    ancial
    -0.77
    ablishment
    -0.75
    ãĥ«
    -0.74
    ervative
    -0.72
    atchewan
    -0.71
    pmwiki
    -0.71
    atoon
    -0.70
    POSITIVE LOGITS
    rell
    1.14
    rol
    1.06
    rians
    0.90
    roph
    0.89
    burn
    0.87
    rian
    0.84
     Ty
    0.84
    win
    0.84
    Ty
    0.80
    rop
    0.80
    Activations Density 0.004%

    No Known Activations