© 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. 12131
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks that need to be done or work that is required

    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
    524
    +0.10
    0.5%
    58
    +0.10
    0.4%
    157
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.10
    0.04
    458
    +0.10
    0.03
    16
    +0.09
    0.02
    Negative Logits
    threat
    -0.73
     stormed
    -0.69
    panic
    -0.67
    majority
    -0.66
    het
    -0.62
     Ukrain
    -0.61
     Targ
    -0.61
    tall
    -0.61
    olina
    -0.61
     derog
    -0.60
    POSITIVE LOGITS
     done
    1.07
     undertaken
    1.07
     underway
    0.95
     expended
    0.94
     performed
    0.87
     collabor
    0.85
    done
    0.85
     groundwork
    0.85
     diligence
    0.84
     preparation
    0.82
    Activations Density 0.269%

    No Known Activations