© 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. 11-RES-JB
    11. 14884
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations of various features or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    comparisons related to vehicle specifications and performance

    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
    Cause
    -0.81
    Population
    -0.77
    isd
    -0.71
    WHO
    -0.70
    Interview
    -0.69
    ERROR
    -0.68
    istical
    -0.68
     contagious
    -0.67
     infectious
    -0.67
    population
    -0.66
    POSITIVE LOGITS
     Panasonic
    1.06
     Jaguar
    1.02
     Samsung
    1.00
     Razer
    0.97
     Thunderbolt
    0.97
     ASUS
    0.96
     its
    0.96
     Mazda
    0.96
     Motorola
    0.95
     Corsair
    0.95
    Activations Density 0.282%

    No Known Activations