© 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. 23150
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "act" and its variations

    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
    PDATE
    -0.85
    yip
    -0.81
    Ń·
    -0.80
     tradem
    -0.76
     millenn
    -0.74
     proble
    -0.74
     tremend
    -0.71
    awaru
    -0.69
    £ı
    -0.68
    ĨĴ
    -0.67
    POSITIVE LOGITS
    ional
    1.21
    uated
    0.99
    uary
    0.99
    act
    0.94
    ors
    0.88
    ivity
    0.88
    ives
    0.87
    uality
    0.86
    ual
    0.86
    uate
    0.86
    Activations Density 0.011%

    No Known Activations