© 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. 11011
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions, responsibilities, and governmental policies

    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
    102
    +0.20
    1.0%
    566
    +0.14
    0.6%
    418
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.11
    55
    +0.14
    0.09
    566
    +0.12
    0.08
    Negative Logits
     srfAttach
    -0.87
     slideshow
    -0.73
     Extension
    -0.71
     Formation
    -0.68
     Technique
    -0.67
     Scrib
    -0.67
     slope
    -0.66
     unfocusedRange
    -0.66
     Explosion
    -0.66
     Scale
    -0.65
    POSITIVE LOGITS
     able
    1.34
     subjected
    1.18
     aware
    1.17
     punished
    1.13
     forgiven
    1.12
     excluded
    1.06
     unable
    1.06
     treated
    1.05
     deprived
    1.03
     wary
    1.01
    Activations Density 0.260%

    No Known Activations