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 49152
    5. 8-RES_FS49152-JB
    6. 46088
    Prev
    Next
    INDEX
    Explanations

    descriptions of complexity and intensity in relationships or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    122
    +0.12
    0.5%
    412
    +0.11
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.12
    0.05
    408
    +0.11
    0.05
    711
    +0.10
    0.03
    Negative Logits
    ques
    -0.82
    steps
    -0.81
    iddles
    -0.76
    busters
    -0.75
    hops
    -0.74
     Surve
    -0.74
     Posts
    -0.72
    yond
    -0.70
     Participants
    -0.69
    ipples
    -0.69
    POSITIVE LOGITS
     tendency
    1.28
     knack
    1.28
     penchant
    1.22
     reputation
    1.19
     relationship
    1.11
     grasp
    1.08
     foothold
    1.04
     affinity
    1.04
     inclination
    1.02
     chance
    1.02
    Activations Density 0.116%

    No Known Activations