© 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. 19404
    Prev
    Next
    INDEX
    Explanations

    instances of the word "from" next to descriptions or explanations of sources or origins

    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
    447
    +0.14
    0.6%
    608
    +0.12
    0.5%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.04
    614
    +0.12
    0.03
    669
    +0.11
    0.03
    Negative Logits
    merce
    -0.82
    fps
    -0.80
    anooga
    -0.76
    idav
    -0.76
    aqu
    -0.72
    olson
    -0.69
    nex
    -0.69
    chairs
    -0.69
    currency
    -0.68
    include
    -0.67
    POSITIVE LOGITS
     afar
    1.13
     nowhere
    0.99
     somewhere
    0.99
     whence
    0.98
     abroad
    0.91
     scratch
    0.90
     obscurity
    0.84
     elsewhere
    0.81
     thence
    0.78
     inside
    0.75
    Activations Density 0.076%

    No Known Activations