© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19397
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical details such as numbers, terms, and actions

    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
    314
    +0.18
    0.8%
    651
    +0.13
    0.6%
    459
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.18
    0.06
    314
    +0.13
    0.00
    526
    +0.13
    0.00
    Negative Logits
     nutshell
    -0.72
     abundantly
    -0.68
    utenberg
    -0.65
     srfAttach
    -0.63
     cannabin
    -0.60
     awake
    -0.58
     Ri
    -0.58
     FAT
    -0.57
     foremost
    -0.56
     Biological
    -0.56
    POSITIVE LOGITS
    ings
    1.94
    ments
    1.73
    ing
    1.56
    ment
    1.50
    ations
    1.48
    ning
    1.34
    ership
    1.31
    ers
    1.30
    downs
    1.29
    ability
    1.27
    Activations Density 0.282%

    No Known Activations