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. 1224
    Prev
    Next
    INDEX
    Explanations

    verbs indicating future events or actions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    551
    +0.18
    0.8%
    139
    +0.10
    0.5%
    188
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.18
    0.11
    139
    +0.10
    0.07
    49
    +0.10
    0.06
    Negative Logits
     praying
    -0.82
     bidding
    -0.80
     raping
    -0.72
     searching
    -0.71
     inspecting
    -0.70
     burying
    -0.70
     dreaming
    -0.69
     digging
    -0.69
     talking
    -0.69
     copying
    -0.69
    POSITIVE LOGITS
     be
    1.20
     coincide
    1.15
     prevail
    1.08
     occur
    1.08
     suffice
    1.08
     arise
    1.07
     vanish
    1.04
     diminish
    1.02
     remain
    1.02
     disappear
    1.01
    Activations Density 0.257%

    No Known Activations