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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19912
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons or justifications

    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
    608
    +0.16
    0.7%
    103
    +0.13
    0.6%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.04
    103
    +0.13
    0.03
    616
    +0.12
    0.03
    Negative Logits
    OLOGY
    -0.80
     ILCS
    -0.77
    nets
    -0.76
    jab
    -0.72
    chn
    -0.71
    anges
    -0.70
    astics
    -0.70
    chin
    -0.70
    ros
    -0.69
    feld
    -0.69
    POSITIVE LOGITS
     preferring
    1.05
     why
    1.04
     inaction
    1.00
     choosing
    0.92
     excluding
    0.89
     favoring
    0.88
     dismissing
    0.86
     existence
    0.85
     omission
    0.85
     wanting
    0.85
    Activations Density 0.075%

    No Known Activations