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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20724
    Prev
    Next
    INDEX
    Explanations

    specific unique characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    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
    alez
    -0.79
    icter
    -0.73
    eway
    -0.70
    breeding
    -0.69
    orial
    -0.69
    ified
    -0.67
     plaque
    -0.66
    imony
    -0.66
    orescence
    -0.65
    aimon
    -0.65
    POSITIVE LOGITS
    ÃĤ
    1.10
    ¢
    1.00
    ©
    0.92
    ³³³³
    0.81
    HL
    0.77
    ¯¯
    0.77
    ��
    0.76
     ����
    0.76
    ³³³³³³³³³³³³³³³³
    0.76
    ¯
    0.75
    Activations Density 0.008%

    No Known Activations