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 24576
    5. 8-RES_FS24576-JB
    6. 11186
    Prev
    Next
    INDEX
    Explanations

    questions about societal issues and urban planning

    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
    285
    +0.15
    0.7%
    166
    +0.10
    0.4%
    6
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.15
    0.06
    6
    +0.10
    0.07
    232
    +0.10
    0.05
    Negative Logits
     arm
    -0.75
     yak
    -0.68
    ikuman
    -0.66
    ishable
    -0.64
    cipled
    -0.63
     pocket
    -0.63
    eared
    -0.62
     corrid
    -0.61
    armed
    -0.61
     coil
    -0.60
    POSITIVE LOGITS
     Surely
    1.25
     Wouldn
    1.19
     Answer
    1.18
     Would
    1.11
     Certainly
    1.10
     Does
    1.10
    Answer
    1.10
     Perhaps
    1.08
     Why
    1.06
     Isn
    1.05
    Activations Density 0.101%

    No Known Activations