© 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. 10-RES-JB
    11. 2195
    Prev
    Next
    INDEX
    Explanations

    triggering phrases focusing on a specific subject matter within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol that signifies a type of response or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Windsor
    -0.76
     Yor
    -0.70
     Suzuki
    -0.67
     Rack
    -0.65
     Roose
    -0.65
     Photographer
    -0.64
     Laurent
    -0.64
     Belfast
    -0.62
     Showdown
    -0.62
     Xan
    -0.62
    POSITIVE LOGITS
    agree
    0.86
    should
    0.84
    rely
    0.84
    ve
    0.82
    s
    0.82
    t
    0.82
    felt
    0.81
    were
    0.81
    ¯¯
    0.81
    require
    0.81
    Activations Density 0.197%

    No Known Activations