© 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. 7980
    Prev
    Next
    INDEX
    Explanations

    past tense verbs referring to specific actions or events

    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
    481
    +0.11
    0.5%
    139
    +0.11
    0.5%
    762
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.11
    0.09
    586
    +0.11
    0.07
    762
    +0.11
    0.08
    Negative Logits
     Mandatory
    -0.69
    classic
    -0.68
     Impact
    -0.66
    regulation
    -0.66
    veyard
    -0.66
     Millennium
    -0.64
     NP
    -0.63
    tones
    -0.62
    services
    -0.61
    necessary
    -0.61
    POSITIVE LOGITS
    'd
    1.20
     thinks
    1.11
     remembers
    1.11
     knew
    1.10
    'll
    1.09
     wondered
    1.07
     knows
    1.06
     admits
    1.03
     grinned
    1.02
     prefers
    1.02
    Activations Density 0.237%

    No Known Activations