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. 23114
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups who have survived traumatic experiences or crises

    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
    288
    +0.14
    0.7%
    571
    +0.12
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.01
    571
    +0.12
    0.01
    32
    +0.10
    0.01
    Negative Logits
    matically
    -0.77
    æ©Ł
    -0.70
    sterdam
    -0.70
    ueller
    -0.67
    brow
    -0.67
    othy
    -0.67
    headed
    -0.66
    azaki
    -0.65
    estic
    -0.65
    ono
    -0.65
    POSITIVE LOGITS
     Survive
    0.88
    Surv
    0.87
     survivors
    0.80
     Survivors
    0.79
     Survivor
    0.77
     crabs
    0.76
    surv
    0.74
    @#&
    0.71
     survivor
    0.69
     Voices
    0.69
    Activations Density 0.016%

    No Known Activations