© 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. 11293
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character or symbol pattern in the text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    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
     Wichita
    -0.73
     Stras
    -0.72
    ellen
    -0.66
    warts
    -0.65
    ignment
    -0.64
    ategic
    -0.63
    enger
    -0.60
     Springfield
    -0.60
     Sly
    -0.60
    espie
    -0.60
    POSITIVE LOGITS
    âĸĵ
    1.16
    ĵ
    1.08
    ¡
    1.05
    DIT
    0.98
    ×Ļ
    0.92
    ×ķ
    0.91
    æµ
    0.88
    BLE
    0.87
    ±
    0.87
    ¼
    0.87
    Activations Density 0.003%

    No Known Activations