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

    Neuronpedia

    Jacobian LensNEW
    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. 7612
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or objects

    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
    289
    +0.13
    0.6%
    68
    +0.12
    0.6%
    526
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.13
    0.01
    114
    +0.12
    0.01
    301
    +0.10
    0.01
    Negative Logits
     Sachs
    -0.68
    NESS
    -0.68
    ÄŁ
    -0.67
     HRC
    -0.66
     Angus
    -0.65
     Chronicle
    -0.63
    NEWS
    -0.63
    USER
    -0.61
    çīĪ
    -0.61
    SOURCE
    -0.60
    POSITIVE LOGITS
    ements
    1.34
    ename
    1.15
    ating
    1.14
    ental
    1.12
    atin
    1.09
    atron
    1.07
    atos
    1.05
    ently
    1.04
    our
    1.02
    ational
    1.02
    Activations Density 0.019%

    No Known Activations