© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 2421
    Prev
    Next
    INDEX
    Explanations

    words related to a single entity or object

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing singularity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.86
    thumbnails
    -0.79
    archives
    -0.75
    idon
    -0.70
    atu
    -0.69
    çī
    -0.68
    imir
    -0.67
    apesh
    -0.67
    types
    -0.66
    chi
    -0.65
    POSITIVE LOGITS
     ounce
    1.27
     dime
    1.23
     penny
    1.05
     inch
    0.98
    THING
    0.96
     trace
    0.83
     shred
    0.83
     slightest
    0.80
     nickel
    0.79
     mention
    0.79
    Activations Density 0.176%

    No Known Activations