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. 530
    Prev
    Next
    INDEX
    Explanations

    information related to missing persons and disappearance cases

    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
    481
    +0.23
    1.1%
    430
    +0.12
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.23
    0.15
    354
    +0.12
    0.12
    430
    +0.11
    0.16
    Negative Logits
    ablishment
    -0.74
    soType
    -0.70
    é¾įå¥ij士
    -0.69
    ãĥķãĤ¡
    -0.67
     awarding
    -0.67
     Akin
    -0.67
     Adds
    -0.66
    ãĥ¢
    -0.65
     illuminating
    -0.64
    Allows
    -0.63
    POSITIVE LOGITS
     disappeared
    1.13
     suffered
    1.12
     underwent
    1.11
     escaped
    1.10
     surrendered
    1.08
     survived
    1.08
     voluntarily
    1.07
     fled
    1.05
     undergo
    1.05
     vanished
    1.00
    Activations Density 3.240%

    No Known Activations