© 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 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. 11098
    Prev
    Next
    INDEX
    Explanations

    information about violent incidents involving shootings and killings

    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
    209
    +0.12
    0.5%
    152
    +0.11
    0.5%
    544
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.12
    0.03
    553
    +0.11
    0.03
    703
    +0.11
    0.03
    Negative Logits
    ð
    -0.72
     Username
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
    ional
    -0.68
    shire
    -0.67
    Else
    -0.66
    ahime
    -0.66
    CN
    -0.65
    Factor
    -0.63
    çļ
    -0.62
    POSITIVE LOGITS
     unarmed
    1.06
     bullets
    0.94
     gunshots
    0.89
     kill
    0.89
     pistol
    0.87
     muzzle
    0.87
     gunfire
    0.86
     killing
    0.86
     handguns
    0.85
     gunshot
    0.84
    Activations Density 0.194%

    No Known Activations