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. 26330
    Prev
    Next
    INDEX
    Explanations

    repeated references to "The" indicating a focus on titles or significant subjects

    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
    447
    +0.25
    1.2%
    481
    +0.22
    1.1%
    362
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.25
    0.05
    142
    +0.22
    0.04
    385
    +0.17
    0.05
    Negative Logits
     beforehand
    -0.86
    æ©
    -0.77
    /"
    -0.76
    omever
    -0.75
    Ò
    -0.74
     thereof
    -0.72
     thereby
    -0.71
    SPONSORED
    -0.71
    iod
    -0.69
     theirs
    -0.69
    POSITIVE LOGITS
    resa
    1.50
    odore
    1.28
    oret
    1.26
     Latest
    1.05
    ories
    1.02
    orem
    1.00
    atre
    0.99
     Basics
    0.97
     easiest
    0.94
     latest
    0.93
    Activations Density 0.123%

    No Known Activations