© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18693
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of a specific character series

    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
    317
    +0.10
    0.5%
    524
    +0.10
    0.5%
    541
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.01
    639
    +0.10
    0.01
    103
    +0.10
    0.01
    Negative Logits
    arious
    -0.82
    arios
    -0.79
    arsity
    -0.75
    ength
    -0.74
    ient
    -0.74
    accompanied
    -0.74
     Brach
    -0.73
    ities
    -0.71
    acea
    -0.71
    iant
    -0.70
    POSITIVE LOGITS
    м
    1.43
    д
    1.27
    в
    1.26
    н
    1.25
    к
    1.24
    л
    1.22
    Ð
    1.20
    ÑĢ
    1.20
    ·
    1.15
    ÑĤ
    1.13
    Activations Density 0.012%

    No Known Activations