Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18557
    Prev
    Next
    INDEX
    Explanations

    terms related to disruptions, difficulties or controversies

    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
    447
    +0.15
    0.7%
    288
    +0.11
    0.5%
    470
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.15
    0.05
    288
    +0.11
    0.06
    225
    +0.10
    0.05
    Negative Logits
    estone
    -0.60
     carrot
    -0.59
    ynski
    -0.58
    aucas
    -0.57
    Percent
    -0.55
     compliment
    -0.55
    cknow
    -0.55
    erville
    -0.54
     blat
    -0.53
    ACTED
    -0.53
    POSITIVE LOGITS
     havoc
    0.91
     amongst
    0.87
     among
    0.84
     akin
    0.75
     wherever
    0.74
     throughout
    0.72
    .<
    0.71
     elsewhere
    0.70
     downstream
    0.68
     upon
    0.68
    Activations Density 0.252%

    No Known Activations