© 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. 1319
    Prev
    Next
    INDEX
    Explanations

    statements highlighting significant challenges or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight sensitive issues or challenges faced by various groups or individuals

    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
    qi
    -0.75
    ohn
    -0.72
    cles
    -0.71
    igger
    -0.68
    aunder
    -0.68
    clair
    -0.67
    heimer
    -0.67
    mol
    -0.66
    OVA
    -0.66
    buster
    -0.65
    POSITIVE LOGITS
    geries
    1.10
    bidden
    1.03
     policymakers
    1.03
     purposes
    1.01
     everyone
    0.93
    gery
    0.92
     starters
    0.91
     beginners
    0.91
     anyone
    0.91
     everybody
    0.89
    Activations Density 0.159%

    No Known Activations