© 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. 21966
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical terms or names

    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
    659
    +0.12
    0.5%
    420
    +0.12
    0.5%
    631
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    631
    +0.12
    0.03
    659
    +0.12
    0.03
    420
    +0.10
    0.03
    Negative Logits
    iewicz
    -0.67
    ãĥ¼ãĥĨ
    -0.64
    ãģį
    -0.63
    etheless
    -0.63
     PRESS
    -0.63
    ĸļ
    -0.62
     containment
    -0.61
    lessly
    -0.61
    uitous
    -0.60
    IFIED
    -0.60
    POSITIVE LOGITS
    achable
    1.42
    aching
    1.26
    levision
    1.24
    achers
    1.21
    acher
    1.20
    legram
    1.17
    legraph
    1.12
    aches
    1.11
    ppo
    1.11
    brate
    1.10
    Activations Density 0.018%

    No Known Activations