© 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. 4-RES-JB
    6. 9342
    Prev
    Next
    INDEX
    Explanations

    details and updates related to technology products and announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to technology product announcements and specifications

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

    No Comments

    Negative Logits
    yll
    -0.65
    agogue
    -0.62
     poems
    -0.61
     deport
    -0.60
     prayed
    -0.60
    agog
    -0.60
     intervened
    -0.58
     injustice
    -0.58
     Auschwitz
    -0.57
    isms
    -0.57
    POSITIVE LOGITS
     Huawei
    0.89
     Nvidia
    0.89
     Xiaomi
    0.89
     OEM
    0.86
     HTC
    0.86
    Samsung
    0.86
    Digital
    0.85
     Samsung
    0.83
     NVIDIA
    0.81
     Snapdragon
    0.80
    Activations Density 2.951%

    No Known Activations