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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7630
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures like transplants and regenerative medicine

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    +0.13
    0.6%
    481
    +0.13
    0.6%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    78
    +0.13
    0.01
    343
    +0.10
    0.01
    Negative Logits
    sem
    -0.78
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.75
    ĪĴ
    -0.73
    PLAY
    -0.73
    MET
    -0.71
     Lank
    -0.70
    adj
    -0.69
    externalActionCode
    -0.68
    zza
    -0.68
     WARN
    -0.68
    POSITIVE LOGITS
     recipient
    1.06
     transplant
    1.03
     surgery
    1.00
     transpl
    0.97
     recipients
    0.96
    ation
    0.94
     surgeries
    0.93
     donor
    0.81
    ectomy
    0.80
    ION
    0.77
    Activations Density 0.028%

    No Known Activations