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. 1803
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    496
    +0.10
    0.5%
    696
    +0.10
    0.4%
    599
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.10
    0.04
    696
    +0.10
    0.04
    524
    +0.09
    0.04
    Negative Logits
     realism
    -0.68
     hoops
    -0.67
     scales
    -0.64
     admitting
    -0.64
     diplom
    -0.64
    hetti
    -0.64
     impulse
    -0.63
     Guinness
    -0.63
     Banner
    -0.60
    onomic
    -0.58
    POSITIVE LOGITS
    gments
    1.20
    eker
    1.19
    ldom
    1.14
    vere
    1.11
    gment
    1.06
    eps
    1.05
    perate
    1.04
    greg
    1.04
    venth
    1.03
    xton
    1.03
    Activations Density 0.413%

    No Known Activations