© 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. 19444
    Prev
    Next
    INDEX
    Explanations

    phrases related to willingness and negotiation

    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
    665
    +0.15
    0.7%
    654
    +0.13
    0.6%
    49
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.04
    49
    +0.13
    0.04
    654
    +0.11
    0.03
    Negative Logits
     Compass
    -0.93
    ////////////////////////////////
    -0.77
    Offline
    -0.72
    _.
    -0.68
    DAQ
    -0.68
     Cars
    -0.66
    tracks
    -0.65
    availability
    -0.65
    lights
    -0.65
    alia
    -0.65
    POSITIVE LOGITS
     accept
    1.32
     sacrifice
    1.32
     tolerate
    1.24
     concede
    1.24
     admit
    1.21
     negotiate
    1.18
     embrace
    1.15
     compromise
    1.15
     cooperate
    1.14
     forgive
    1.14
    Activations Density 0.075%

    No Known Activations