© 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. 2264
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character sequence "âĢ" followed by a digit which could refer to a specific coding or formatting pattern

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of specific phrases or symbols indicating strong emphasis or agreement

    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
     boarding
    -0.68
     guiActiveUnfocused
    -0.66
     lodging
    -0.64
    creen
    -0.63
     Palest
    -0.62
     shroud
    -0.60
     residence
    -0.60
     Aid
    -0.60
     fame
    -0.60
     RAD
    -0.59
    POSITIVE LOGITS
    ¡
    0.99
    £
    0.91
    ¢
    0.88
    ¬
    0.87
    º
    0.87
    ½
    0.81
    soType
    0.81
    âĢķ
    0.81
    ł
    0.81
    agree
    0.81
    Activations Density 0.486%

    No Known Activations