© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10108
    Prev
    Next
    INDEX
    Explanations

    Words related to personal opinions and critiques in a detailed context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    306
    +0.12
    0.6%
    653
    +0.12
    0.5%
    634
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.08
    720
    +0.12
    0.08
    679
    +0.11
    0.09
    Negative Logits
    ĸļ
    -1.02
    ļéĨĴ
    -0.78
    ãĥĺ
    -0.75
    çĭ
    -0.74
    æ©Ł
    -0.71
    ä¸Ĭ
    -0.69
    encia
    -0.69
    »Ĵ
    -0.68
    WIND
    -0.67
    ANCE
    -0.66
    POSITIVE LOGITS
     but
    1.17
     But
    1.14
    but
    1.12
     maybe
    0.98
     Maybe
    0.93
     Others
    0.92
     However
    0.92
    But
    0.91
     depending
    0.90
     BUT
    0.89
    Activations Density 0.945%

    No Known Activations