© 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 49152
    5. 8-RES_FS49152-JB
    6. 45571
    Prev
    Next
    INDEX
    Explanations

    terms related to physical characteristics or attributes of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.13
    0.6%
    724
    +0.12
    0.6%
    535
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.13
    0.02
    535
    +0.12
    0.01
    673
    +0.12
    0.01
    Negative Logits
     Nadu
    -0.75
    ACTED
    -0.70
    icago
    -0.69
    ansen
    -0.68
     Cron
    -0.66
    scl
    -0.65
    overs
    -0.65
     Twins
    -0.64
    sie
    -0.61
     mammoth
    -0.60
    POSITIVE LOGITS
     properties
    0.93
    properties
    0.80
    uation
    0.79
    ality
    0.77
    Changed
    0.76
    iveness
    0.76
    ious
    0.76
    istry
    0.73
    ually
    0.72
    ter
    0.71
    Activations Density 0.010%

    No Known Activations