© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15131
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    oai_token-act-pair · gpt-3.5-turbo

    character sequences or symbols, possibly those used in special formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manif
    -0.87
    undai
    -0.81
    espie
    -0.79
    esville
    -0.79
    buquerque
    -0.78
    geries
    -0.77
     Pwr
    -0.76
    zees
    -0.76
    ierrez
    -0.75
     intrigue
    -0.75
    POSITIVE LOGITS
    ا
    1.02
    à¤
    0.98
    åº
    0.96
    ł
    0.93
    å¿
    0.92
    ãģ
    0.90
    į
    0.89
    ĭ
    0.89
    Ĩ
    0.88
    ¶
    0.88
    Activations Density 0.008%

    No Known Activations