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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11697
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions and states of organizations or individuals

    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
    447
    +0.15
    0.7%
    696
    +0.12
    0.5%
    338
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.15
    0.04
    705
    +0.12
    0.04
    691
    +0.10
    0.03
    Negative Logits
    ongs
    -0.67
    olon
    -0.66
     Viol
    -0.65
     staples
    -0.63
     meticulous
    -0.60
     rad
    -0.60
    ouched
    -0.59
     viol
    -0.58
     Cutter
    -0.58
    gress
    -0.56
    POSITIVE LOGITS
     financially
    1.11
     situation
    0.87
     predicament
    0.86
    mma
    0.81
     dilemma
    0.79
     footing
    0.78
     lately
    0.76
     facing
    0.75
    iquid
    0.72
     considering
    0.71
    Activations Density 0.222%

    No Known Activations