© 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. 4-RES-JB
    11. 2336
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names and potentially associated numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical data or statistics

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

    No Comments

    Negative Logits
    xual
    -0.80
    undai
    -0.74
    ean
    -0.73
    phrine
    -0.71
    ĸļ
    -0.70
    mble
    -0.67
    pressure
    -0.67
    tumblr
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    irie
    -0.64
    POSITIVE LOGITS
    asted
    0.97
    00
    0.83
    OTAL
    0.81
    asts
    0.80
    ature
    0.79
    _.
    0.77
     Minutes
    0.76
    TI
    0.76
    ovember
    0.75
    dfx
    0.75
    Activations Density 0.028%

    No Known Activations