© 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. 1-RES-JB
    11. 10438
    Prev
    Next
    INDEX
    Explanations

    the word "ok" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    the expression of agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lav
    -0.79
     Legions
    -0.78
    Topics
    -0.71
    models
    -0.67
    ãĥĺãĥ©
    -0.64
    è¦ļéĨĴ
    -0.62
    Engineers
    -0.60
     cort
    -0.59
    senal
    -0.59
    STE
    -0.58
    POSITIVE LOGITS
    ok
    1.13
    lahoma
    1.10
    arak
    0.96
    oks
    0.92
    imus
    0.90
    orea
    0.90
    wana
    0.87
    andi
    0.87
    atis
    0.86
    aku
    0.86
    Activations Density 0.008%

    No Known Activations