© 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. 2400
    Prev
    Next
    INDEX
    Explanations

    connections or relationships between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections between entities

    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
    SHA
    -0.93
    ©¶æ¥µ
    -0.89
    hend
    -0.79
    ADRA
    -0.76
    HE
    -0.75
     horm
    -0.72
    LECT
    -0.70
    enza
    -0.70
    ouse
    -0.69
    heast
    -0.69
    POSITIVE LOGITS
     vice
    0.80
    /
    0.72
     features
    0.67
     experiences
    0.64
    nery
    0.59
     exhibitions
    0.58
    cellaneous
    0.58
     laundry
    0.57
     baggage
    0.57
     theaters
    0.57
    Activations Density 0.408%

    No Known Activations