© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19845
    Prev
    Next
    INDEX
    Explanations

    ingredients and recipes related to lemon

    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
    525
    +0.10
    0.5%
    603
    +0.09
    0.4%
    136
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.10
    0.01
    326
    +0.09
    0.01
    603
    +0.09
    0.01
    Negative Logits
    afety
    -0.90
    PsyNetMessage
    -0.81
    Downloadha
    -0.79
    ADRA
    -0.79
    ULTS
    -0.76
    razil
    -0.74
    dit
    -0.74
     Pension
    -0.73
    BLIC
    -0.72
    ITNESS
    -0.71
    POSITIVE LOGITS
     juice
    1.20
    ade
    1.00
     peel
    0.98
    fruit
    0.95
     bal
    0.93
     squee
    0.90
     juices
    0.88
     wedge
    0.84
    bread
    0.82
     wed
    0.81
    Activations Density 0.016%

    No Known Activations