© 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. 7-RES-JB
    11. 7888
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or performing a task

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the conjunction 'and' and their corresponding actions or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.82
    lich
    -0.79
    arth
    -0.76
    ibl
    -0.72
    ANC
    -0.71
    ukong
    -0.69
    ĨĴ
    -0.67
    existence
    -0.66
    laughter
    -0.64
    una
    -0.64
    POSITIVE LOGITS
     THEN
    1.18
     then
    0.97
     thereby
    0.93
     thus
    0.85
     shove
    0.85
     sends
    0.85
     parcel
    0.84
     decide
    0.83
     recreate
    0.81
     spit
    0.81
    Activations Density 0.258%

    No Known Activations