© 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. 12963
    Prev
    Next
    INDEX
    Explanations

    descriptions using the words "slanted" or "sloping"

    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
    659
    +0.09
    0.4%
    128
    +0.09
    0.4%
    556
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.09
    0.01
    128
    +0.09
    0.02
    523
    +0.09
    0.02
    Negative Logits
     pleas
    -0.69
    ICLE
    -0.69
    ãģ®éŃĶ
    -0.67
    IFIC
    -0.66
    NEY
    -0.64
    BLIC
    -0.64
    HCR
    -0.63
    terms
    -0.62
    lishing
    -0.62
    bell
    -0.60
    POSITIVE LOGITS
    ashes
    1.17
    asher
    1.17
    udge
    1.15
    anted
    1.14
    ippers
    1.13
    ugs
    1.12
    ipper
    1.12
    ugg
    1.12
    inging
    1.11
    icker
    1.11
    Activations Density 0.013%

    No Known Activations