© 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. 2-RES-JB
    11. 850
    Prev
    Next
    INDEX
    Explanations

    unusual, non-standard characters or symbols

    oai_token-act-pair · gpt-4-turbo

    phrases in foreign languages with special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -1.04
    inelli
    -0.80
     CLSID
    -0.78
    enegger
    -0.76
     Murdoch
    -0.73
     tee
    -0.72
     Unch
    -0.72
     Catalyst
    -0.70
    raints
    -0.70
    awaru
    -0.69
    POSITIVE LOGITS
    Ĩ
    0.90
    å¸
    0.86
    ®
    0.84
    º
    0.82
    µ
    0.81
    ļ
    0.81
    ĩ
    0.80
    ł
    0.79
    į
    0.78
    ±
    0.77
    Activations Density 0.007%

    No Known Activations