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 3072
    5. 8-RES_FS3072-JB
    6. 1332
    Prev
    Next
    INDEX
    Explanations

    host-related words or terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    526
    +0.10
    0.5%
    519
    +0.10
    0.5%
    415
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.07
    415
    +0.10
    0.04
    519
    +0.10
    0.04
    Negative Logits
     Rite
    -0.72
    istar
    -0.67
     msec
    -0.63
     pave
    -0.62
    iage
    -0.60
     prud
    -0.60
     braking
    -0.60
    pend
    -0.58
     Imper
    -0.58
     shortcut
    -0.57
    POSITIVE LOGITS
    esses
    1.05
    ilities
    0.99
    ess
    0.92
    names
    0.86
    ility
    0.83
    itors
    0.82
    name
    0.82
    el
    0.80
    emark
    0.79
    Guest
    0.78
    Activations Density 0.813%

    No Known Activations