© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1953
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning that something has been highlighted or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "pointed out."

    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
     nose
    -0.85
    phrine
    -0.85
     noses
    -0.76
     handshake
    -0.76
     lips
    -0.74
     stabilized
    -0.73
     fingert
    -0.72
     froze
    -0.71
     hips
    -0.71
     gaze
    -0.69
    POSITIVE LOGITS
    null
    0.79
    fitted
    0.77
    س
    0.76
    tics
    0.76
    posts
    0.75
    >>>>
    0.75
    wards
    0.71
    WARD
    0.70
     è£ıè
    0.70
    LESS
    0.69
    Activations Density 0.048%

    No Known Activations