© 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. 11095
    Prev
    Next
    INDEX
    Explanations

    structural elements like dashes and other characters used for separating or emphasizing text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various formatting markers or separators within the text

    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
    iller
    -0.83
    illed
    -0.69
    agos
    -0.69
     vision
    -0.66
    stood
    -0.65
    aron
    -0.63
    nery
    -0.63
    oku
    -0.63
     divers
    -0.62
     passing
    -0.61
    POSITIVE LOGITS
    ------------
    1.18
    -------------
    1.14
    ---------------
    1.10
    --------------
    1.10
    ---
    1.09
    ===
    1.04
    --+
    1.04
    ==
    1.03
    ============
    1.03
    ---------
    1.02
    Activations Density 0.012%

    No Known Activations