© 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. 7-RES-JB
    11. 20699
    Prev
    Next
    INDEX
    Explanations

    references to places or people with 'Lang' in their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lang" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compensated
    -0.73
    hift
    -0.70
    ItemTracker
    -0.69
    awaru
    -0.68
    ģĸ
    -0.64
    Ĥª
    -0.63
    ×ij
    -0.63
     listener
    -0.62
     parity
    -0.60
     eleph
    -0.59
    POSITIVE LOGITS
    ford
    1.15
    strom
    1.09
    ley
    1.08
    enberg
    1.07
     Lang
    0.98
    ued
    0.97
    dale
    0.95
    don
    0.94
    ston
    0.92
    gow
    0.92
    Activations Density 0.020%

    No Known Activations