© 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. 11-RES-JB
    11. 15042
    Prev
    Next
    INDEX
    Explanations

    instances of the string "âĢ¦" followed by a number, perhaps indicating emphasis or importance in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the special character "âĢ¦"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.83
    ady
    -0.67
    uder
    -0.65
    aque
    -0.65
    appa
    -0.62
    ãĥŁ
    -0.61
    ãĥĭ
    -0.61
    ibi
    -0.60
    Thumbnail
    -0.60
    ãĥģ
    -0.59
    POSITIVE LOGITS
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    0.86
     Continue
    0.83
     Anyway
    0.81
     Continued
    0.76
     Suddenly
    0.76
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.75
     Trying
    0.75
     Journalists
    0.75
     Basically
    0.74
    etc
    0.71
    Activations Density 0.045%

    No Known Activations