© 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. 4488
    Prev
    Next
    INDEX
    Explanations

    technical specifications and comparisons between electronic devices

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

    comparisons and contrasts between products, particularly in specifications and features

    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
    cffffcc
    -0.62
     contagious
    -0.60
     rab
    -0.58
     statistic
    -0.58
    Population
    -0.57
    ashington
    -0.56
    NN
    -0.56
     perpetrated
    -0.54
     conspir
    -0.54
    Cause
    -0.54
    POSITIVE LOGITS
     Asus
    0.94
     ASUS
    0.92
     Panasonic
    0.90
     Samsung
    0.90
     Xiaomi
    0.90
     Razer
    0.88
     its
    0.88
     Corsair
    0.88
     OLED
    0.86
     Lenovo
    0.86
    Activations Density 0.374%

    No Known Activations