© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    words that appear to be corrupted or have special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate special encoding or formatting issues

    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
    othal
    -0.76
     ostr
    -0.75
    inx
    -0.70
    oresc
    -0.68
    achelor
    -0.68
    ackets
    -0.68
    ulhu
    -0.68
    apsed
    -0.67
     recl
    -0.67
    iferation
    -0.67
    POSITIVE LOGITS
     ��������
    1.00
     ����
    0.99
    ¢
    0.81
     �
    0.77
    dinand
    0.75
    checks
    0.73
    bold
    0.73
    Rust
    0.71
    ��
    0.71
    Rah
    0.71
    Activations Density 0.004%

    No Known Activations