© 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. 12-RES-JB
    11. 3172
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms indicating significance or quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDES
    -0.78
    ahs
    -0.77
    racuse
    -0.69
    onds
    -0.67
    ËĪ
    -0.67
    ses
    -0.65
    )))
    -0.65
    hens
    -0.63
    oks
    -0.61
    sten
    -0.61
    POSITIVE LOGITS
     news
    1.05
     fodder
    0.92
     enough
    0.90
     progress
    0.88
     insofar
    0.85
     territory
    0.85
     timing
    0.84
     because
    0.79
     precedent
    0.78
     momentum
    0.77
    Activations Density 0.270%

    No Known Activations