© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1232
    Prev
    Next
    INDEX
    Explanations

    the word "dual" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to dual functionality or dual systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UFF
    -0.82
    FORE
    -0.79
    ONEY
    -0.74
    âĸĪâĸĪ
    -0.72
     Warehouse
    -0.72
    Dialogue
    -0.71
     Learns
    -0.70
    ################
    -0.69
     Simulator
    -0.68
    ATHER
    -0.68
    POSITIVE LOGITS
    ples
    0.90
    ity
    0.89
    fold
    0.87
    ities
    0.85
    edged
    0.82
    xes
    0.80
     sided
    0.78
     wielding
    0.78
     simultaneous
    0.77
    footed
    0.75
    Activations Density 0.017%

    No Known Activations