© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3646
    Prev
    Next
    INDEX
    Explanations

    references to the anthrax attacks that occurred post-9/11

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    385
    +0.13
    0.6%
    127
    +0.12
    0.6%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.01
    335
    +0.12
    0.01
    127
    +0.11
    0.01
    Negative Logits
    VICE
    -0.88
    SPONSORED
    -0.75
    ãĥĩãĤ£
    -0.69
    Assembly
    -0.69
     guiActiveUnfocused
    -0.68
    FORMATION
    -0.68
     Undead
    -0.66
    UTION
    -0.66
    ABLE
    -0.65
     Mast
    -0.65
    POSITIVE LOGITS
    rax
    1.44
    opoulos
    1.14
    rac
    1.13
    ropy
    1.12
    ony
    1.08
    ologies
    1.07
    ology
    1.03
    oine
    1.01
    orns
    0.97
    opl
    0.94
    Activations Density 0.020%

    No Known Activations