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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2809
    Prev
    Next
    INDEX
    Explanations

    mentions of services or activities being provided or available to people

    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
    659
    +0.13
    0.6%
    496
    +0.11
    0.5%
    190
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.05
    190
    +0.11
    0.05
    701
    +0.10
    0.04
    Negative Logits
    pole
    -0.69
     totality
    -0.64
    medium
    -0.63
    edged
    -0.62
     slic
    -0.60
    Closure
    -0.59
     Equality
    -0.57
     corners
    -0.56
     conventions
    -0.56
    paralle
    -0.56
    POSITIVE LOGITS
    adow
    1.29
    asuring
    1.26
    asure
    1.19
    adows
    1.16
    asured
    1.15
    zzo
    1.13
    imei
    1.12
    cca
    1.11
    aning
    1.06
    asures
    1.05
    Activations Density 0.451%

    No Known Activations