© 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. 12551
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletter subscriptions and acknowledgments

    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
    49
    +0.12
    0.6%
    572
    +0.10
    0.5%
    492
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.02
    211
    +0.10
    0.01
    208
    +0.09
    0.02
    Negative Logits
    amaz
    -0.65
    adium
    -0.63
     moot
    -0.61
     Gamb
    -0.61
     Aberdeen
    -0.61
    mong
    -0.60
     Faust
    -0.60
     Crim
    -0.59
    itism
    -0.58
    imm
    -0.58
    POSITIVE LOGITS
    're
    1.18
    'll
    1.07
    've
    0.99
     may
    0.85
    'd
    0.85
     MUST
    0.81
     can
    0.81
     shalt
    0.78
     might
    0.74
     must
    0.71
    Activations Density 0.022%

    No Known Activations