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 3072
    5. 8-RES_FS3072-JB
    6. 1448
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts

    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
    288
    +0.12
    0.5%
    508
    +0.12
    0.5%
    235
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.09
    508
    +0.12
    0.07
    235
    +0.10
    0.06
    Negative Logits
    uble
    -0.76
    regate
    -0.74
     Grayson
    -0.73
     Territories
    -0.70
     Hamm
    -0.68
    Publisher
    -0.66
    */(
    -0.65
    rings
    -0.65
     rand
    -0.64
     Strongh
    -0.63
    POSITIVE LOGITS
     patients
    1.13
     doctor
    1.11
     doctors
    1.10
     Patients
    1.07
     patient
    1.05
     practitioner
    1.05
     diagnoses
    1.02
     physician
    1.00
     Patient
    0.97
     care
    0.96
    Activations Density 0.648%

    No Known Activations