© 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. 13072
    Prev
    Next
    INDEX
    Explanations

    news-related keywords and references to newsletter sign-ups

    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
    679
    +0.16
    0.7%
    373
    +0.11
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.16
    0.03
    656
    +0.11
    0.02
    586
    +0.11
    0.02
    Negative Logits
    amily
    -0.68
     nerv
    -0.65
    »Ĵ
    -0.61
    ibr
    -0.61
     grease
    -0.60
    RC
    -0.60
    IRO
    -0.59
    ooked
    -0.58
     bare
    -0.58
    ulu
    -0.58
    POSITIVE LOGITS
    ificantly
    1.53
    ificant
    1.38
    atories
    1.37
    atures
    1.32
    ific
    1.30
    posts
    1.18
    ature
    1.10
    ging
    1.04
    alling
    1.03
    Sign
    1.02
    Activations Density 0.014%

    No Known Activations