© 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 24576
    5. 8-RES_FS24576-JB
    6. 9888
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and emotional 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
    285
    +0.11
    0.5%
    447
    +0.10
    0.5%
    197
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.11
    0.04
    285
    +0.10
    0.04
    690
    +0.10
    0.04
    Negative Logits
    interrupted
    -0.70
     conquered
    -0.67
     downed
    -0.67
    rough
    -0.65
    asio
    -0.65
    essor
    -0.64
    hens
    -0.64
    ahs
    -0.64
     healed
    -0.64
    essed
    -0.63
    POSITIVE LOGITS
     hypocrisy
    0.88
     hypocritical
    0.82
     insofar
    0.81
     arrogance
    0.78
    headed
    0.74
     counterproductive
    0.74
     enough
    0.73
     because
    0.73
     irresponsible
    0.72
     misrepresent
    0.71
    Activations Density 0.168%

    No Known Activations