© 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 24576
    9. 8-RES_FS24576-JB
    11. 12053
    Prev
    Next
    INDEX
    Explanations

    medical conditions and healthcare-related terms

    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
    447
    +0.24
    1.1%
    420
    +0.10
    0.5%
    29
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.24
    0.05
    461
    +0.10
    0.04
    5
    +0.10
    0.04
    Negative Logits
    Tes
    -0.67
     consolation
    -0.58
    dding
    -0.58
     forgetting
    -0.57
     theirs
    -0.57
    ]."
    -0.57
     tack
    -0.56
     hers
    -0.55
    gone
    -0.55
    )."
    -0.55
    POSITIVE LOGITS
     consists
    1.35
     refers
    1.30
     represents
    1.19
     comprises
    1.15
     consisted
    1.13
     combines
    1.05
     originated
    1.02
     describes
    1.01
     embodies
    1.01
     encompasses
    1.01
    Activations Density 0.331%

    No Known Activations