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. 11784
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organization names starting with "Af"

    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
    288
    +0.13
    0.6%
    311
    +0.13
    0.6%
    187
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.13
    0.01
    187
    +0.13
    0.01
    103
    +0.11
    0.01
    Negative Logits
    soDeliveryDate
    -0.84
     guiActiveUnfocused
    -0.82
    INESS
    -0.80
     MFT
    -0.67
     Passion
    -0.66
    ORED
    -0.66
    è¯
    -0.64
    channelAvailability
    -0.62
     endlessly
    -0.62
     greenhouse
    -0.61
    POSITIVE LOGITS
    rica
    1.32
    rika
    1.20
    ghan
    1.18
    raid
    1.14
    rican
    1.14
    icion
    1.13
    onso
    1.12
    resh
    1.03
    riend
    1.03
    riad
    1.03
    Activations Density 0.014%

    No Known Activations