© 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 3072
    5. 8-RES_FS3072-JB
    6. 262
    Prev
    Next
    INDEX
    Explanations

    terms related to skin conditions and medical reactions, specifically those involving chemical exposures or sun sensitivity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    290
    +0.13
    0.6%
    679
    +0.12
    0.6%
    420
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.13
    0.06
    546
    +0.12
    0.06
    707
    +0.12
    0.06
    Negative Logits
    ysis
    -0.72
    orts
    -0.71
    odcast
    -0.70
    pping
    -0.69
    ient
    -0.69
    ppe
    -0.69
    pell
    -0.67
    ipop
    -0.66
    appy
    -0.65
    oyd
    -0.64
    POSITIVE LOGITS
    ––
    1.15
    âĸº
    0.81
     Rapp
    0.80
    _>
    0.78
    anooga
    0.75
    ————
    0.75
    _-
    0.74
    achu
    0.73
    taboola
    0.72
    summary
    0.70
    Activations Density 0.335%

    No Known Activations