© 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. 8146
    Prev
    Next
    INDEX
    Explanations

    terms related to LGBTQ+ issues and rights

    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
    481
    +0.12
    0.5%
    384
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.12
    0.02
    288
    +0.10
    0.02
    199
    +0.10
    0.02
    Negative Logits
    EMS
    -0.78
    Dispatch
    -0.76
    urers
    -0.74
    GV
    -0.73
    atche
    -0.70
    unes
    -0.69
    ULE
    -0.68
    ammy
    -0.67
    assic
    -0.64
    VIS
    -0.63
    POSITIVE LOGITS
    osexual
    1.07
    bian
    0.89
    bians
    0.84
    dar
    0.84
    ophobic
    0.82
    ophobia
    0.80
     slurs
    0.79
    xual
    0.78
    ity
    0.77
     pedoph
    0.76
    Activations Density 0.032%

    No Known Activations