© 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. 18417
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically names of places

    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
    23
    +0.12
    0.5%
    555
    +0.10
    0.4%
    194
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.01
    555
    +0.10
    0.01
    129
    +0.10
    0.01
    Negative Logits
    stocks
    -0.79
    orld
    -0.72
     Abyssal
    -0.67
    birds
    -0.66
    Ïī
    -0.66
    ãģĭ
    -0.65
     flo
    -0.65
    strap
    -0.65
    FACE
    -0.64
     Pearl
    -0.61
    POSITIVE LOGITS
    ablish
    1.52
    ablished
    1.51
    imate
    1.41
    imating
    1.33
    imates
    1.32
    uary
    1.20
    imated
    1.17
    imation
    1.11
    ablishment
    1.11
    rogen
    1.02
    Activations Density 0.009%

    No Known Activations