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. 1022
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations and travel destinations

    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
    +0.10
    0.5%
    362
    +0.10
    0.5%
    731
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.10
    0.05
    362
    +0.10
    0.05
    288
    +0.10
    0.04
    Negative Logits
    thood
    -0.85
    =-=-=-=-
    -0.78
    apter
    -0.77
    osponsors
    -0.75
    Coin
    -0.74
    zos
    -0.71
    kos
    -0.70
    zees
    -0.70
    Phys
    -0.69
    intent
    -0.69
    POSITIVE LOGITS
     courtyard
    1.23
     surroundings
    1.19
     countryside
    1.19
     town
    1.15
     suburb
    1.14
     woodland
    1.11
     confines
    1.11
     rural
    1.11
     streets
    1.09
     valley
    1.09
    Activations Density 0.174%

    No Known Activations