© 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. 3-RES-JB
    11. 11267
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings or processes

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal proceedings and trials

    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
     Qiao
    -0.70
    imoto
    -0.68
    hered
    -0.68
     socially
    -0.67
    roots
    -0.67
    mac
    -0.66
    apo
    -0.65
    CRE
    -0.64
    Regular
    -0.63
    PATH
    -0.63
    POSITIVE LOGITS
    rial
    0.79
    ength
    0.72
     Crusade
    0.69
    aneously
    0.69
    iminary
    0.68
    adiator
    0.67
    ysis
    0.66
     Procedures
    0.65
    igham
    0.65
    ipel
    0.65
    Activations Density 0.009%

    No Known Activations