© 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. 17361
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings with special characters, combined with numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters and punctuation that suggest emphasis or non-standard formatting

    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
    itar
    -0.61
     Maher
    -0.60
     consumption
    -0.59
     epigen
    -0.58
    itialized
    -0.57
    adan
    -0.57
     Burnett
    -0.57
     targeting
    -0.57
     strategically
    -0.56
     staging
    -0.56
    POSITIVE LOGITS
    ^^
    1.00
    «
    0.94
    ^
    0.91
    Si
    0.88
     âĸł
    0.88
     tion
    0.81
    RFC
    0.80
    sic
    0.79
    âĢ¢âĢ¢
    0.79
    20439
    0.78
    Activations Density 0.115%

    No Known Activations