© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2342
    Prev
    Next
    INDEX
    Explanations

    words related to directional flow or movement, particularly focusing on the concept of being "bound."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    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

    Neuron Alignment
    Index
    Value
    % of L₁
    408
    +0.13
    0.6%
    365
    +0.11
    0.5%
    561
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.01
    585
    +0.11
    0.01
    593
    +0.11
    0.01
    Negative Logits
    pload
    -0.83
    ptive
    -0.83
    oult
    -0.78
    adr
    -0.77
    cffff
    -0.77
    ptives
    -0.73
    nikov
    -0.73
    sonian
    -0.72
    Skin
    -0.71
    ochet
    -0.70
    POSITIVE LOGITS
     lanes
    1.25
     lane
    0.99
     traffic
    0.95
     motorists
    0.91
     Interstate
    0.89
     roadway
    0.87
     drivers
    0.85
     Amtrak
    0.85
     highways
    0.85
     driver
    0.82
    Activations Density 0.027%

    No Known Activations