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 24576
    5. 8-RES_FS24576-JB
    6. 23637
    Prev
    Next
    INDEX
    Explanations

    words related to sprouting or growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    129
    +0.12
    0.6%
    162
    +0.11
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.12
    0.02
    251
    +0.11
    0.01
    128
    +0.10
    0.01
    Negative Logits
     resonance
    -0.65
     Passage
    -0.65
    ographers
    -0.64
    rium
    -0.64
     blow
    -0.63
    WARE
    -0.62
    */(
    -0.60
    ographer
    -0.60
     sorely
    -0.59
    ãģ¦
    -0.59
    POSITIVE LOGITS
    inters
    1.19
    ained
    1.13
    outed
    1.09
    inkle
    1.08
    atche
    1.08
    outing
    1.05
    acer
    1.03
    outs
    1.02
    ays
    1.02
    anca
    1.01
    Activations Density 0.015%

    No Known Activations