© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving advice or instructions

    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
    393
    +0.11
    0.5%
    762
    +0.10
    0.5%
    715
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.11
    0.07
    139
    +0.10
    0.05
    718
    +0.10
    0.06
    Negative Logits
    Args
    -0.71
    grain
    -0.66
     Upper
    -0.66
     Albion
    -0.64
    Late
    -0.62
     Caller
    -0.61
    Oracle
    -0.60
    MM
    -0.60
    VG
    -0.59
    omen
    -0.59
    POSITIVE LOGITS
     create
    1.13
     withdraw
    1.10
     earn
    1.07
     participate
    1.06
     spend
    1.06
     expel
    1.05
     indulge
    1.04
     drown
    1.04
     perform
    1.04
     declare
    1.03
    Activations Density 0.294%

    No Known Activations