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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1476
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and opinions

    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
    734
    +0.13
    0.6%
    63
    +0.12
    0.5%
    605
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.07
    734
    +0.12
    0.05
    49
    +0.10
    0.06
    Negative Logits
    boards
    -0.85
    iann
    -0.80
    ributes
    -0.68
    uries
    -0.66
    ackle
    -0.66
    imon
    -0.66
    iaries
    -0.66
     hugs
    -0.65
    urrencies
    -0.65
    tions
    -0.65
    POSITIVE LOGITS
     misunderstood
    1.10
     misunderstanding
    1.10
     underest
    1.07
     wrong
    1.07
     miscon
    1.02
     mistaken
    1.01
     Wrong
    0.99
     overest
    0.97
     misunderstand
    0.96
     hypocr
    0.93
    Activations Density 0.758%

    No Known Activations