© 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. 6438
    Prev
    Next
    INDEX
    Explanations

    phrases related to a method, approach, or direction

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "way" in different contexts or phrases

    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
    encer
    -0.71
    ı
    -0.67
    anmar
    -0.65
     Nanto
    -0.65
    rake
    -0.64
    icio
    -0.62
    elve
    -0.62
    uster
    -0.61
    ulu
    -0.59
    akov
    -0.59
    POSITIVE LOGITS
    finding
    0.98
    fare
    0.92
    point
    0.92
     WAY
    0.86
    ward
    0.80
    points
    0.78
     DAM
    0.70
    PASS
    0.70
    WARD
    0.69
    RAY
    0.68
    Activations Density 0.043%

    No Known Activations