© 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. 8696
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious texts and forgiveness

    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
    285
    +0.13
    0.6%
    710
    +0.11
    0.5%
    297
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.13
    0.05
    100
    +0.11
    0.05
    297
    +0.11
    0.05
    Negative Logits
    é¾
    -0.89
    ongo
    -0.85
    DAQ
    -0.82
    achev
    -0.78
    assian
    -0.76
    ularity
    -0.74
     takeaway
    -0.74
    Focus
    -0.74
    ookie
    -0.73
    ãĤ£
    -0.70
    POSITIVE LOGITS
     whence
    1.33
     viz
    1.31
     thence
    1.22
     wherein
    1.14
     whereby
    1.10
     whilst
    1.05
     etc
    1.05
     yea
    1.02
     notwithstanding
    1.01
     whereas
    1.01
    Activations Density 0.279%

    No Known Activations