© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18766
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by adjectives indicating degree or manner

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endants
    -0.74
    hiba
    -0.70
    Cause
    -0.69
    Netflix
    -0.68
    Parents
    -0.68
    Companies
    -0.67
    asonic
    -0.65
    Ur
    -0.65
     dstg
    -0.64
    Voice
    -0.64
    POSITIVE LOGITS
    efficiency
    1.14
     lieu
    1.06
    juries
    1.06
     terms
    1.04
     midfield
    1.01
     unison
    0.98
    effic
    0.98
     front
    0.95
     spite
    0.93
     favor
    0.91
    Activations Density 0.107%

    No Known Activations