© 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. 6-RES-JB
    11. 21753
    Prev
    Next
    INDEX
    Explanations

    superlative achievements or records

    oai_token-act-pair · gpt-3.5-turbo

    instances of record-setting achievements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.71
     parted
    -0.62
    )=(
    -0.61
    unity
    -0.60
    dial
    -0.60
     differently
    -0.60
     CONTIN
    -0.60
    Appearance
    -0.59
    iHUD
    -0.59
    actionDate
    -0.58
    POSITIVE LOGITS
    liest
    0.92
     fastest
    0.85
    avorite
    0.82
     charts
    0.77
     tallest
    0.76
     category
    0.74
     rankings
    0.73
     contemporaries
    0.72
    Hig
    0.71
     worldwide
    0.70
    Activations Density 0.678%

    No Known Activations