© 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. 20220
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format

    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
    314
    +0.18
    0.8%
    640
    +0.16
    0.7%
    373
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.18
    0.02
    627
    +0.16
    0.02
    160
    +0.13
    0.02
    Negative Logits
     tox
    -0.71
     Ferr
    -0.71
     Bian
    -0.68
     Trent
    -0.67
     Ku
    -0.67
     Scientology
    -0.66
     spoof
    -0.66
     tint
    -0.64
     invari
    -0.64
     Jem
    -0.63
    POSITIVE LOGITS
    5
    1.13
    3
    1.11
    2
    1.09
    8
    1.09
    7
    1.08
    4
    1.07
    1
    1.05
    9
    1.05
    10
    1.04
    13
    1.04
    Activations Density 0.033%

    No Known Activations