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. 517
    Prev
    Next
    INDEX
    Explanations

    political and governmental references

    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
    436
    +0.10
    0.5%
    325
    +0.10
    0.5%
    380
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.06
    304
    +0.10
    0.05
    55
    +0.10
    0.07
    Negative Logits
    enium
    -0.84
    asonic
    -0.71
    uth
    -0.68
    onz
    -0.65
    strom
    -0.65
     Horses
    -0.64
     msec
    -0.64
    nin
    -0.63
    sonian
    -0.62
    ength
    -0.60
    POSITIVE LOGITS
     impacted
    1.07
     affected
    1.07
     hardest
    0.97
    hots
    0.96
     singled
    0.95
    priority
    0.93
    affected
    0.90
     concern
    0.87
     exempted
    0.87
    ulnerable
    0.85
    Activations Density 0.855%

    No Known Activations