© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2490
    Prev
    Next
    INDEX
    Explanations

    dates related to significant events, particularly those related to political and military activities

    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
    223
    +0.12
    0.6%
    178
    +0.11
    0.5%
    240
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.02
    178
    +0.11
    0.02
    337
    +0.10
    0.02
    Negative Logits
    Reviewer
    -0.66
     juggling
    -0.64
    BACK
    -0.61
     stricken
    -0.59
     segreg
    -0.59
    holder
    -0.59
     Hearts
    -0.58
     cruc
    -0.57
     caution
    -0.56
    holders
    -0.56
    POSITIVE LOGITS
    hens
    1.02
    opus
    0.97
    ibel
    0.96
    urnal
    0.93
    ools
    0.91
    hew
    0.91
    alez
    0.90
    agen
    0.89
    ¶
    0.88
    eteenth
    0.86
    Activations Density 0.010%

    No Known Activations