© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    words related to critique or evaluation

    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
    561
    +0.13
    0.6%
    738
    +0.10
    0.4%
    66
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.03
    284
    +0.10
    0.03
    373
    +0.09
    -0.01
    Negative Logits
    Updated
    -0.71
    STEP
    -0.65
    Õ
    -0.63
    smith
    -0.63
    è£ħ
    -0.62
    éĥ
    -0.60
    ELS
    -0.60
    osate
    -0.58
    éĸ
    -0.58
    aneers
    -0.58
    POSITIVE LOGITS
    usalem
    0.92
    chel
    0.90
    rigan
    0.84
    rero
    0.82
    rera
    0.80
    lein
    0.79
    gency
    0.78
    stellar
    0.78
    igible
    0.76
    culus
    0.76
    Activations Density 0.068%

    No Known Activations