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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45429
    Prev
    Next
    INDEX
    Explanations

    references to the Tiananmen Square protests

    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
    420
    +0.13
    0.6%
    167
    +0.12
    0.6%
    267
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.13
    0.01
    538
    +0.12
    0.01
    284
    +0.11
    0.01
    Negative Logits
    IDER
    -0.78
    ESSION
    -0.75
     pars
    -0.66
     mileage
    -0.66
    IVES
    -0.63
    ESH
    -0.61
     recess
    -0.61
    ardon
    -0.61
    ftime
    -0.60
    PASS
    -0.60
    POSITIVE LOGITS
    jin
    1.42
    jing
    1.25
     Tian
    1.21
    yu
    1.05
    ept
    1.05
     Xia
    0.98
     Xiang
    0.98
     Jing
    0.97
    hai
    0.97
    hao
    0.94
    Activations Density 0.004%

    No Known Activations