© 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. 4-RES-JB
    11. 10401
    Prev
    Next
    INDEX
    Explanations

    phrases related to visualization and imagination

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or items in a list format

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

    No Comments

    Negative Logits
    undai
    -0.87
    alsa
    -0.87
    icum
    -0.86
    atur
    -0.83
    laus
    -0.82
    etheless
    -0.82
    ulhu
    -0.76
    urat
    -0.76
    assic
    -0.75
    iped
    -0.75
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.20
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.02
    ï¸ı
    0.81
    âĸł
    0.75
     âĢ¢
    0.74
    Publisher
    0.72
     Advertisement
    0.71
     DATA
    0.71
    ternity
    0.68
    Includes
    0.68
    Activations Density 0.017%

    No Known Activations