© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20059
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and counter-terrorism efforts

    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
    373
    +0.12
    0.6%
    683
    +0.10
    0.4%
    353
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.05
    659
    +0.10
    0.05
    373
    +0.09
    -0.02
    Negative Logits
    SPONSORED
    -0.81
    ħĭ
    -0.68
     "$:/
    -0.66
    wcs
    -0.60
     births
    -0.60
     readable
    -0.60
     campuses
    -0.60
     comprom
    -0.60
     encl
    -0.58
    CLASS
    -0.58
    POSITIVE LOGITS
    rio
    0.76
    utsche
    0.75
    heim
    0.68
    beck
    0.67
    ão
    0.65
    ential
    0.65
    ér
    0.65
     Saud
    0.65
    eros
    0.64
    feld
    0.64
    Activations Density 0.179%

    No Known Activations