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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9432
    Prev
    Next
    INDEX
    Explanations

    Finnish words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    non-English characters and their corresponding sequences in text, indicating a focus on specific linguistic features or styles

    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
     Deadpool
    -0.95
     Boxing
    -0.94
     Rollins
    -0.91
     Phillies
    -0.84
     Queens
    -0.83
     Rhodes
    -0.79
     Richmond
    -0.78
     Bacon
    -0.77
     Furious
    -0.77
     Gotham
    -0.76
    POSITIVE LOGITS
    ä
    1.53
    ikk
    1.39
    emi
    1.38
    isu
    1.38
    inen
    1.35
    iku
    1.30
    aan
    1.29
    ku
    1.29
    aa
    1.28
    eni
    1.26
    Activations Density 0.172%

    No Known Activations