© 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. 21946
    Prev
    Next
    INDEX
    Explanations

    economic terms related to retirement savings

    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
    +0.13
    0.6%
    464
    +0.12
    0.6%
    35
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.13
    0.01
    11
    +0.12
    0.01
    326
    +0.11
    0.01
    Negative Logits
    tics
    -0.74
    Ŀ
    -0.67
     Cortana
    -0.63
     Morsi
    -0.60
     degraded
    -0.59
     Demand
    -0.58
     Tibet
    -0.57
     Lenovo
    -0.57
     Overwatch
    -0.57
    ı
    -0.56
    POSITIVE LOGITS
    bard
    1.44
    stein
    1.22
    bart
    1.18
    schild
    1.01
    cliffe
    0.98
    igan
    0.96
    child
    0.92
    sten
    0.91
    feld
    0.90
    kj
    0.90
    Activations Density 0.019%

    No Known Activations