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

    Neuronpedia

    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. 1-RES-JB
    11. 532
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that might be related to technical errors or formatting issues in text

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard text characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alez
    -0.72
    apers
    -0.72
    oded
    -0.70
    orial
    -0.70
    ologically
    -0.69
    ified
    -0.68
    ebin
    -0.67
    orative
    -0.66
    lessly
    -0.66
    guided
    -0.65
    POSITIVE LOGITS
    ÃĤ
    1.28
    ¢
    0.97
    ¯¯¯¯
    0.89
    ³³³³
    0.88
    ³³³³³³³³
    0.85
    ³³³³³³³³³³³³³³³³
    0.85
    ¯¯
    0.83
    Ãī
    0.82
     ����
    0.82
    ©
    0.81
    Activations Density 0.008%

    No Known Activations