© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 4420
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Tang"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Tang" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.98
    ktop
    -0.78
     mileage
    -0.71
    LEASE
    -0.70
    cki
    -0.69
    etheless
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    âķIJâķIJ
    -0.66
    vous
    -0.64
    Downloadha
    -0.63
    POSITIVE LOGITS
    Tang
    1.23
     Tang
    1.03
    ivil
    0.97
    entially
    0.95
    arov
    0.91
    atari
    0.87
    atar
    0.87
    ents
    0.86
    iful
    0.85
    raph
    0.84
    Activations Density 0.007%

    No Known Activations