© 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. 3-RES-JB
    11. 335
    Prev
    Next
    INDEX
    Explanations

    patterns of characters in a structured format that look like file paths or commands

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numerical and special character patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.50
    EVA
    -0.46
    aturdays
    -0.44
     warranties
    -0.41
    yip
    -0.41
    oulos
    -0.40
    everal
    -0.39
    ãĥ¼ãĥĨãĤ£
    -0.39
     conclud
    -0.38
    ĪĴ
    -0.38
    POSITIVE LOGITS
    __
    0.46
    ">
    0.41
    cd
    0.40
    bb
    0.40
    bm
    0.39
    _
    0.38
    ,-
    0.37
    bt
    0.37
    /)
    0.37
    data
    0.36
    Activations Density 0.955%

    No Known Activations