© 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. 8871
    Prev
    Next
    INDEX
    Explanations

    strong action verbs related to obtaining or benefiting from something

    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
    314
    +0.15
    0.7%
    7
    +0.13
    0.6%
    372
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.15
    0.02
    7
    +0.13
    0.02
    223
    +0.13
    0.02
    Negative Logits
     refusing
    -0.61
     separating
    -0.60
     tubing
    -0.58
     leaning
    -0.58
     collapsing
    -0.57
     Kro
    -0.57
     decom
    -0.57
     submar
    -0.56
     hospitalized
    -0.56
     hanged
    -0.56
    POSITIVE LOGITS
     rewards
    1.05
     reap
    0.99
     dividends
    0.94
     royalties
    0.92
    efully
    0.91
    advant
    0.85
     benefits
    0.85
    minster
    0.84
    eful
    0.84
     praise
    0.83
    Activations Density 0.078%

    No Known Activations