© 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. 16868
    Prev
    Next
    INDEX
    Explanations

    year values

    oai_token-act-pair · gpt-3.5-turbo

    specific years mentioned in the text and their related 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
     lawy
    -0.78
    atem
    -0.74
    yout
    -0.70
    cott
    -0.66
    abilia
    -0.66
    creen
    -0.66
     cha
    -0.65
    itton
    -0.61
     cop
    -0.60
    ype
    -0.60
    POSITIVE LOGITS
     onwards
    0.92
    -'
    0.80
    âĢ²
    0.80
     dollars
    0.73
     GDP
    0.72
    adjusted
    0.70
     (%
    0.70
     Dollars
    0.69
    regate
    0.69
     alone
    0.69
    Activations Density 0.199%

    No Known Activations