© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    information or details about events happening in a specific place or time

    oai_token-act-pair · gpt-3.5-turbo

    structured information and details about events or activities

    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
     retracted
    -0.98
     corpus
    -0.90
     redund
    -0.87
     deposition
    -0.86
     contraction
    -0.86
     quantitative
    -0.83
     discredited
    -0.82
     extracted
    -0.82
     substant
    -0.81
     regression
    -0.80
    POSITIVE LOGITS
    Tickets
    1.72
     Tickets
    1.55
     Admission
    1.50
    Located
    1.41
     Located
    1.32
    Saturday
    1.30
    Visit
    1.28
    Come
    1.26
    Registration
    1.25
     Parking
    1.24
    Activations Density 0.307%

    No Known Activations