© 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 3072
    9. 8-RES_FS3072-JB
    11. 248
    Prev
    Next
    INDEX
    Explanations

    dates or time related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    98
    +0.13
    0.6%
    369
    +0.10
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.13
    0.11
    703
    +0.10
    0.07
    172
    +0.10
    0.08
    Negative Logits
    ertain
    -0.92
    isible
    -0.83
    tick
    -0.80
    xx
    -0.79
    eg
    -0.79
    psy
    -0.77
    lez
    -0.76
    aez
    -0.74
    Duration
    -0.73
    Grade
    -0.72
    POSITIVE LOGITS
     refusing
    0.83
     allegations
    0.83
     failing
    0.82
     admitting
    0.82
     discovering
    0.81
     authorities
    0.80
     unsuccessfully
    0.80
     mistakenly
    0.80
     they
    0.80
     undergoing
    0.78
    Activations Density 0.889%

    No Known Activations