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. 12194
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and perspectives

    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
    446
    +0.12
    0.6%
    447
    +0.12
    0.6%
    720
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.12
    0.09
    43
    +0.12
    0.06
    546
    +0.12
    0.07
    Negative Logits
     guiActiveUn
    -0.81
    rontal
    -0.71
    OGR
    -0.68
    FactoryReloaded
    -0.68
    OME
    -0.67
    icial
    -0.65
    inct
    -0.64
    chell
    -0.64
    iq
    -0.64
    ipel
    -0.63
    POSITIVE LOGITS
     but
    1.00
     regardless
    0.97
     huh
    0.95
     albeit
    0.89
    but
    0.82
     eh
    0.82
     irrespective
    0.82
     especially
    0.81
     whereas
    0.80
     though
    0.77
    Activations Density 0.305%

    No Known Activations