© 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. 22052
    Prev
    Next
    INDEX
    Explanations

    terms related to various features and functionalities of motion and voice recognition technology

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.20
    0.9%
    440
    +0.11
    0.5%
    694
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.20
    0.02
    326
    +0.11
    0.04
    232
    +0.11
    0.04
    Negative Logits
    terday
    -0.89
    aughters
    -0.71
     offence
    -0.69
     republican
    -0.69
     omission
    -0.67
     unheard
    -0.66
     constitu
    -0.66
    ioned
    -0.64
     wreck
    -0.64
     duly
    -0.64
    POSITIVE LOGITS
    Tool
    1.16
    Bench
    1.15
    Sense
    1.14
    Chat
    1.14
    Server
    1.14
    Guard
    1.13
    Grid
    1.11
    Stream
    1.11
    Tools
    1.10
    Boost
    1.10
    Activations Density 0.202%

    No Known Activations