© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 101
    Prev
    Next
    INDEX
    Explanations

    economic and financial content

    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
    +0.12
    0.6%
    79
    +0.11
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.12
    0.03
    35
    +0.11
    0.03
    43
    +0.10
    0.03
    Negative Logits
    cha
    -0.62
    lass
    -0.61
    ,...
    -0.61
    RM
    -0.58
    verbs
    -0.57
    -,
    -0.56
    cell
    -0.56
    :(
    -0.56
    qv
    -0.56
    sword
    -0.56
    POSITIVE LOGITS
     respectively
    0.96
    depending
    0.90
     depending
    0.87
     carbohyd
    0.71
     whichever
    0.63
     entrants
    0.60
    SPONSORED
    0.58
     aspects
    0.57
     according
    0.56
    atever
    0.56
    Activations Density 0.160%

    No Known Activations