© 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. 18168
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Parrot" and related terms such as "parrot welfare" and "parrot organization"

    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
    145
    +0.12
    0.5%
    515
    +0.12
    0.5%
    60
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.12
    0.02
    145
    +0.12
    0.02
    60
    +0.10
    0.02
    Negative Logits
    sonian
    -0.79
    ħĭ
    -0.74
    ARDS
    -0.71
     Carbuncle
    -0.69
    éĹĺ
    -0.67
    =]
    -0.67
    hirt
    -0.66
     dwar
    -0.66
    ģĸ
    -0.65
    士
    -0.65
    POSITIVE LOGITS
    agraph
    1.34
    anoia
    1.25
    vati
    1.19
    allel
    1.15
    alysis
    1.12
    cel
    1.08
    agon
    1.05
    amount
    1.04
    cells
    1.02
    liament
    0.99
    Activations Density 0.015%

    No Known Activations