© 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. 8968
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political and academic contexts

    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
    59
    +0.13
    0.6%
    721
    +0.13
    0.6%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.01
    288
    +0.13
    0.01
    289
    +0.12
    0.00
    Negative Logits
    GMT
    -0.76
    itives
    -0.69
    ãģĤ
    -0.69
    ETF
    -0.67
    UE
    -0.67
    GB
    -0.63
    Downloadha
    -0.63
    iesel
    -0.61
    اÙĦ
    -0.61
    allo
    -0.59
    POSITIVE LOGITS
    ministic
    1.16
    odox
    1.05
    pent
    0.86
    bos
    0.85
    ogeneous
    0.83
    ries
    0.83
    rier
    0.81
    osexual
    0.81
    iatrics
    0.81
    gent
    0.80
    Activations Density 0.026%

    No Known Activations