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. 733
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals and locations

    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
    +0.29
    1.5%
    481
    +0.24
    1.3%
    288
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.11
    481
    +0.24
    0.08
    15
    +0.13
    0.08
    Negative Logits
     UNCLASSIFIED
    -0.84
     pse
    -0.72
    theless
    -0.64
     looph
    -0.64
    etheless
    -0.61
    lvl
    -0.61
    anwhile
    -0.61
     Azerb
    -0.60
     actionGroup
    -0.59
     cryst
    -0.59
    POSITIVE LOGITS
     Belfast
    0.88
     âĢº
    0.73
    âĢİ
    0.72
     âĢİ
    0.69
     Posted
    0.68
     amid
    0.65
    utterstock
    0.65
     Copyright
    0.64
     tonight
    0.64
     Tuesday
    0.63
    Activations Density 0.694%

    No Known Activations