© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1677
    Prev
    Next
    INDEX
    Explanations

    special characters (such as arrows) followed by letters in a continuous sequence

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters indicating emphasis or importance

    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
     microphone
    -0.63
     minim
    -0.60
     GPS
    -0.60
    ozy
    -0.60
     trainers
    -0.60
     pastry
    -0.58
     microphones
    -0.58
     Ukrain
    -0.58
     shack
    -0.57
     horizont
    -0.57
    POSITIVE LOGITS
    £
    1.01
    ¡
    1.01
    Ĵ
    0.95
    ķ
    0.89
    ¢
    0.87
    ¤
    0.87
    IJ
    0.87
    ª
    0.86
    Ĭ
    0.86
    ı
    0.85
    Activations Density 0.389%

    No Known Activations