© 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. 11-RES-JB
    11. 11175
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and political processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     tomorrow
    -1.02
     earlier
    -0.91
     soon
    -0.90
     yesterday
    -0.88
     later
    -0.88
     tonight
    -0.77
     beforehand
    -0.73
     sooner
    -0.71
     Later
    -0.69
     2022
    -0.69
    POSITIVE LOGITS
     steadily
    0.92
     relentlessly
    0.84
     tirelessly
    0.79
     spor
    0.78
     consistently
    0.77
     innumerable
    0.75
     ranging
    0.75
     inconsist
    0.75
     intermitt
    0.72
     varying
    0.71
    Activations Density 0.740%

    No Known Activations