© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14760
    Prev
    Next
    INDEX
    Explanations

    direct speech actions and communication verbs like 'tell' and 'talk'

    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
    411
    +0.10
    0.5%
    680
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.10
    0.04
    411
    +0.10
    0.03
    604
    +0.10
    0.03
    Negative Logits
    ovable
    -0.60
    oshenko
    -0.60
     princip
    -0.60
    apsed
    -0.60
    irable
    -0.59
    isol
    -0.59
    BE
    -0.58
    Desktop
    -0.58
     }}
    -0.57
    edes
    -0.57
    POSITIVE LOGITS
     myself
    1.24
     my
    0.85
     politely
    0.81
     him
    0.75
     enqu
    0.71
     quizz
    0.70
    yss
    0.69
    daq
    0.66
     inquire
    0.66
     nervously
    0.66
    Activations Density 0.249%

    No Known Activations