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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1082
    Prev
    Next
    INDEX
    Explanations

    potential actions or decisions related to socioeconomic issues and policies

    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
    101
    +0.11
    0.5%
    218
    +0.10
    0.5%
    441
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.11
    0.07
    147
    +0.10
    0.07
    101
    +0.10
    0.07
    Negative Logits
    osc
    -0.63
    ||||
    -0.58
    scope
    -0.57
    Ùĩ
    -0.56
    neg
    -0.56
    roads
    -0.56
    ãģł
    -0.55
    thro
    -0.54
     Ùħ
    -0.54
    ãģ®å®
    -0.54
    POSITIVE LOGITS
    bestos
    1.42
    piring
    1.34
    semb
    1.32
    phalt
    1.29
    pects
    1.27
    ylum
    1.22
    piration
    1.18
    semble
    1.16
    king
    1.14
    ymm
    1.11
    Activations Density 0.239%

    No Known Activations