Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8309
    Prev
    Next
    INDEX
    Explanations

    words related to technology and innovation, specifically focusing on autonomous vehicles and intellectual property disputes

    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
    102
    +0.12
    0.5%
    640
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.12
    0.04
    102
    +0.11
    0.04
    152
    +0.10
    0.03
    Negative Logits
    ulhu
    -0.74
     Chains
    -0.71
    OUGH
    -0.69
     Ribbon
    -0.69
     Lever
    -0.68
     BB
    -0.67
     Rath
    -0.66
     ribbon
    -0.66
     Starr
    -0.66
     Rise
    -0.66
    POSITIVE LOGITS
    destruct
    1.25
    proclaimed
    1.24
    imposed
    1.23
    esteem
    1.17
    contained
    1.15
    decl
    1.14
    righteous
    1.13
    awareness
    1.12
    appointed
    1.12
    expression
    1.11
    Activations Density 0.029%

    No Known Activations