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. 23558
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social activism against discrimination

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.43
    2.4%
    373
    +0.30
    1.7%
    407
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.43
    0.13
    756
    +0.30
    -0.05
    373
    +0.09
    -0.10
    Negative Logits
     âĢº
    -0.50
    PRE
    -0.47
    ococ
    -0.47
    æ©Ł
    -0.45
     Entered
    -0.44
    sty
    -0.43
    NYSE
    -0.43
    ranch
    -0.43
    wcsstore
    -0.43
    DCS
    -0.42
    POSITIVE LOGITS
     meanwhile
    0.85
     moreover
    0.68
     however
    0.66
     therefore
    0.57
    anwhile
    0.55
     though
    0.53
     Lastly
    0.51
     meantime
    0.49
     furthermore
    0.49
     likewise
    0.49
    Activations Density 2.204%

    No Known Activations