© 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. 9-RES-JB
    11. 19759
    Prev
    Next
    INDEX
    Explanations

    dates and schedule-related information

    oai_token-act-pair · gpt-3.5-turbo

    future-oriented statements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atmosp
    -0.73
     Skies
    -0.73
     flyers
    -0.69
     Shal
    -0.68
     congr
    -0.65
     accuses
    -0.63
     lineback
    -0.61
    inia
    -0.61
     investigates
    -0.61
     fundra
    -0.60
    POSITIVE LOGITS
     somehow
    1.09
     actually
    1.08
     invalid
    0.95
     suddenly
    0.93
    actually
    0.92
     nevertheless
    0.82
     incorrect
    0.82
     insufficient
    0.80
     replaced
    0.80
     indeed
    0.79
    Activations Density 0.587%

    No Known Activations