© 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. 22359
    Prev
    Next
    INDEX
    Explanations

    number codes embedded in text

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or codes

    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
    istically
    -0.88
    estine
    -0.83
    owicz
    -0.67
    think
    -0.67
    corn
    -0.66
    leck
    -0.66
     Sands
    -0.64
    igham
    -0.64
    uyomi
    -0.63
    blind
    -0.62
    POSITIVE LOGITS
     ILCS
    0.96
    mph
    0.83
    20439
    0.80
     dB
    0.78
    é¾
    0.74
    artment
    0.73
    rup
    0.73
    rehensive
    0.69
    lectic
    0.69
    KB
    0.67
    Activations Density 0.046%

    No Known Activations