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

    Neuronpedia

    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. 689
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Jake"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jake."

    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
     conduc
    -0.74
    amera
    -0.70
     subst
    -0.65
    Ħ¢
    -0.65
    arily
    -0.65
     systematic
    -0.65
    iary
    -0.63
     authoritative
    -0.63
    ributed
    -0.63
    sound
    -0.62
    POSITIVE LOGITS
     Jake
    0.96
    glers
    0.95
    imaru
    0.83
     Skywalker
    0.81
     McGee
    0.81
    antine
    0.81
    ansas
    0.77
    Jake
    0.76
    unin
    0.75
     Gy
    0.75
    Activations Density 0.006%

    No Known Activations