Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 230
    Prev
    Next
    INDEX
    Explanations

    phrases related to job applications and career experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    198
    +0.10
    0.5%
    540
    +0.09
    0.4%
    678
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.17
    540
    +0.09
    0.14
    575
    +0.09
    0.13
    Negative Logits
    collect
    -0.75
    Interstitial
    -0.69
    eca
    -0.68
     Oo
    -0.68
    Ô
    -0.65
     Jamaica
    -0.65
     Peb
    -0.64
    cart
    -0.63
    gard
    -0.63
    imgur
    -0.60
    POSITIVE LOGITS
     roles
    1.09
     vacancies
    1.07
     vacancy
    1.01
     jobs
    1.01
     vacated
    1.00
     job
    1.00
     duties
    1.00
     assignments
    0.94
     hire
    0.91
     unemploy
    0.90
    Activations Density 5.139%

    No Known Activations