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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13479
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or entities named "Wil"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Wil" or related references to places and people associated with that name

    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
     Butterfly
    -0.81
    ItemTracker
    -0.72
    oral
    -0.71
    yrinth
    -0.69
     shatter
    -0.69
    æĸ¹
    -0.69
     crush
    -0.68
     Carbuncle
    -0.68
    âĶģ
    -0.67
     Parables
    -0.67
    POSITIVE LOGITS
    mot
    1.02
    mington
    1.02
    ibr
    0.96
    fred
    0.96
    lem
    0.92
    lette
    0.90
    Wil
    0.89
    leys
    0.88
    ney
    0.86
    bury
    0.85
    Activations Density 0.011%

    No Known Activations