© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's ability to accomplish a task or achieve a goal

    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
    718
    +0.16
    0.7%
    608
    +0.15
    0.7%
    49
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.16
    0.04
    718
    +0.15
    0.04
    665
    +0.14
    0.04
    Negative Logits
     Respons
    -0.75
     Actions
    -0.70
    LES
    -0.68
     Concern
    -0.67
    prem
    -0.67
    backs
    -0.67
     Forward
    -0.65
     Perspect
    -0.65
     Closing
    -0.65
    grounds
    -0.64
    POSITIVE LOGITS
     convince
    1.38
     overcome
    1.37
     achieve
    1.29
     penetrate
    1.27
     survive
    1.25
     accomplish
    1.24
     evade
    1.21
     infiltrate
    1.18
     persuade
    1.16
     obtain
    1.13
    Activations Density 0.086%

    No Known Activations