Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 883
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing uncertainty or seeking guidance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    699
    +0.11
    0.5%
    195
    +0.10
    0.5%
    374
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.09
    60
    +0.10
    0.07
    483
    +0.10
    0.07
    Negative Logits
    room
    -0.64
    oubted
    -0.64
     ........
    -0.60
    odder
    -0.59
    piece
    -0.59
    peak
    -0.59
    iculture
    -0.58
    ceptions
    -0.58
    izu
    -0.57
    UM
    -0.57
    POSITIVE LOGITS
    soever
    1.04
    beit
    0.96
    ls
    0.92
     much
    0.91
    itzer
    0.88
    ells
    0.87
    ling
    0.82
    ever
    0.82
    much
    0.76
     prevalent
    0.74
    Activations Density 0.558%

    No Known Activations