© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9890
    Prev
    Next
    INDEX
    Explanations

    instructions or steps for a DIY project involving household items or food preparation

    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
    475
    +0.14
    0.6%
    245
    +0.11
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.05
    351
    +0.11
    0.04
    326
    +0.10
    0.06
    Negative Logits
     Kahn
    -0.78
    DEM
    -0.77
     Samar
    -0.76
    åŃ
    -0.74
    ISC
    -0.71
    HAHAHAHA
    -0.69
     Koran
    -0.69
    Discussion
    -0.69
    MQ
    -0.67
     presided
    -0.66
    POSITIVE LOGITS
     moisture
    1.39
     seams
    1.19
     thicker
    1.15
     thickness
    1.12
     adhesive
    1.11
     pores
    1.09
     fibers
    1.08
     surfaces
    1.07
     coating
    1.06
     silicone
    1.06
    Activations Density 0.592%

    No Known Activations