© 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. 8549
    Prev
    Next
    INDEX
    Explanations

    descriptions of criminal acts and investigations

    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
    218
    +0.10
    0.5%
    378
    +0.10
    0.4%
    637
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.05
    551
    +0.10
    0.05
    264
    +0.10
    0.04
    Negative Logits
     concluding
    -0.78
     nutshell
    -0.66
     Readers
    -0.62
     Balanced
    -0.61
     striking
    -0.61
     roadmap
    -0.61
     Recovery
    -0.59
     Voting
    -0.59
     Fishing
    -0.58
     Passive
    -0.58
    POSITIVE LOGITS
    upon
    0.95
     resembled
    0.80
     owns
    0.79
     specializes
    0.78
    oping
    0.76
     presumably
    0.76
     resembles
    0.75
    Äĩ
    0.75
     supposedly
    0.74
    nown
    0.74
    Activations Density 0.252%

    No Known Activations