© 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 EvalsExportsinterp-engineNEWAPI 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. 14605
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles or hindrances in a process

    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
    122
    +0.13
    0.6%
    379
    +0.11
    0.5%
    3
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.13
    0.04
    379
    +0.11
    0.04
    665
    +0.10
    0.03
    Negative Logits
    lat
    -0.79
    ocene
    -0.77
    worn
    -0.74
    Sham
    -0.72
    lich
    -0.71
    arse
    -0.71
    oft
    -0.69
    olate
    -0.68
    variable
    -0.67
    itars
    -0.65
    POSITIVE LOGITS
     progress
    1.07
     accessing
    1.01
     access
    0.97
     digestion
    0.96
     uptake
    0.89
     efforts
    0.84
     completion
    0.84
     attempts
    0.84
     entry
    0.83
     entrance
    0.82
    Activations Density 0.155%

    No Known Activations