© 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. 4-RES-JB
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    keywords related to surveillance and security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data or information processing and analysis

    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
    ],"
    -0.63
    tnc
    -0.63
    )",
    -0.60
    upper
    -0.57
    20439
    -0.55
    uminati
    -0.55
    LOD
    -0.54
    EStream
    -0.53
     beginning
    -0.53
    docker
    -0.53
    POSITIVE LOGITS
    quartered
    0.74
    cknowled
    0.73
    ogether
    0.72
     Ago
    0.71
    hetically
    0.68
    pecially
    0.67
    ONSORED
    0.67
    itionally
    0.65
    ually
    0.65
    cially
    0.64
    Activations Density 0.539%

    No Known Activations