© 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. 2-RES-JB
    11. 10429
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "forums"

    oai_token-act-pair · gpt-3.5-turbo

    references to communities or groups characterized by the term "mums."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srf
    -0.70
     resemb
    -0.66
     plates
    -0.64
    AST
    -0.62
     Guatem
    -0.62
    jri
    -0.61
     ste
    -0.61
    RAW
    -0.61
    resp
    -0.58
    \\\\\\\\\\\\\\\\
    -0.58
    POSITIVE LOGITS
    chool
    1.05
    ums
    1.02
    essage
    0.99
    uit
    0.97
    atsu
    0.94
    atis
    0.92
    ourcing
    0.91
    paces
    0.90
    uitous
    0.88
    mith
    0.88
    Activations Density 0.006%

    No Known Activations