© 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. 18393
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to software development and video game elements

    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
    640
    +0.29
    1.5%
    160
    +0.20
    1.0%
    314
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.13
    160
    +0.20
    0.13
    107
    +0.20
    0.11
    Negative Logits
     Clause
    -0.96
     Mobil
    -0.92
     Coalition
    -0.88
     Tunnel
    -0.82
     Campaign
    -0.82
     Conc
    -0.81
     Char
    -0.79
     Labour
    -0.79
     Integrity
    -0.79
     Fin
    -0.79
    POSITIVE LOGITS
    nor
    1.24
    facebook
    1.22
    Advertisements
    1.19
    else
    1.18
    cause
    1.16
    reply
    1.16
    http
    1.15
    please
    1.13
    dyl
    1.13
    yeah
    1.13
    Activations Density 0.347%

    No Known Activations