© 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. 10173
    Prev
    Next
    INDEX
    Explanations

    information related to video game achievements and mechanics

    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
    373
    +0.17
    0.8%
    599
    +0.10
    0.5%
    642
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.06
    6
    +0.10
    0.05
    160
    +0.10
    0.05
    Negative Logits
     UNCLASSIFIED
    -0.85
    hene
    -0.78
    icrobial
    -0.71
    earchers
    -0.70
    hani
    -0.70
    manuel
    -0.69
    arching
    -0.69
    BER
    -0.68
    asse
    -0.68
     articulate
    -0.67
    POSITIVE LOGITS
    Appearances
    1.21
    Trivia
    1.14
    Gallery
    1.11
    episode
    1.04
    Contents
    1.02
    pmwiki
    1.01
    Characters
    1.01
     Edit
    0.95
    Episode
    0.95
    Gameplay
    0.91
    Activations Density 0.291%

    No Known Activations