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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25671
    Prev
    Next
    INDEX
    Explanations

    the word "distribution" in various forms and contexts

    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
    288
    +0.13
    0.6%
    167
    +0.13
    0.6%
    615
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    615
    +0.13
    0.01
    31
    +0.13
    0.01
    597
    +0.11
    0.01
    Negative Logits
    glers
    -1.21
    swick
    -0.81
     Cage
    -0.80
    ppo
    -0.67
     ABE
    -0.66
    fter
    -0.63
     Slater
    -0.63
     scratch
    -0.63
    ENA
    -0.63
     thumbs
    -0.62
    POSITIVE LOGITS
    ributed
    1.58
    ribut
    1.56
    ribution
    1.49
    rict
    1.47
    inguished
    1.43
    ribute
    1.39
    illery
    1.34
    inct
    1.32
    raction
    1.30
    ortion
    1.27
    Activations Density 0.004%

    No Known Activations