© 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. 12943
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and health

    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
    289
    +0.12
    0.6%
    85
    +0.10
    0.5%
    501
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.02
    289
    +0.10
    0.01
    501
    +0.10
    0.01
    Negative Logits
    BIL
    -0.78
    ãĥ´
    -0.74
    éĹĺ
    -0.72
     Progressive
    -0.70
    ELY
    -0.70
     Paw
    -0.67
    ãģ®éŃĶ
    -0.66
    cmp
    -0.66
    eers
    -0.65
    ndra
    -0.65
    POSITIVE LOGITS
    osate
    1.57
    osph
    1.31
    ysics
    1.25
    antom
    1.19
    obia
    1.16
    tml
    1.06
    inx
    1.01
    ttp
    1.01
    oros
    0.97
    onds
    0.97
    Activations Density 0.013%

    No Known Activations