© 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 1536
    9. 8-RES_FS1536-JB
    11. 1027
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and financial discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    370
    +0.12
    0.5%
    481
    +0.10
    0.5%
    336
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.12
    0.09
    43
    +0.10
    0.07
    720
    +0.10
    0.09
    Negative Logits
    enthal
    -0.68
     LF
    -0.62
    OND
    -0.57
    SPA
    -0.57
    CLOSE
    -0.56
    oir
    -0.56
     (>
    -0.55
    wan
    -0.55
     (-
    -0.55
    Actor
    -0.55
    POSITIVE LOGITS
    into
    0.80
    because
    0.67
    since
    0.66
    depending
    0.66
    than
    0.65
    when
    0.64
    inducing
    0.64
    according
    0.63
    bet
    0.62
    to
    0.62
    Activations Density 1.951%

    No Known Activations