© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9774
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or judgment

    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
    373
    +0.25
    1.3%
    689
    +0.11
    0.6%
    233
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.25
    -0.02
    750
    +0.11
    0.03
    671
    +0.09
    0.03
    Negative Logits
    ultane
    -0.59
     secondly
    -0.56
    iliated
    -0.56
    asio
    -0.55
    hower
    -0.53
    ophon
    -0.53
    ogens
    -0.52
     someday
    -0.51
    ONY
    -0.51
    fall
    -0.51
    POSITIVE LOGITS
     Cage
    0.49
     Opinion
    0.49
     cookie
    0.48
    cookie
    0.47
     msec
    0.47
    ãħĭ
    0.47
     Wrap
    0.47
     Coulter
    0.46
     Passive
    0.46
     Cyn
    0.45
    Activations Density 0.268%

    No Known Activations