© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19980
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of value

    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
    444
    +0.09
    0.4%
    496
    +0.09
    0.4%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.09
    0.03
    444
    +0.09
    0.02
    285
    +0.09
    0.02
    Negative Logits
    jen
    -0.90
    éĹĺ
    -0.67
     Zimmer
    -0.64
     silence
    -0.63
    uthor
    -0.63
     Meadows
    -0.63
     wip
    -0.62
    riter
    -0.62
    ¯¯¯¯
    -0.61
    ELF
    -0.61
    POSITIVE LOGITS
     proposition
    1.21
     Proposition
    0.98
     propositions
    0.94
     value
    0.90
    umed
    0.79
     Value
    0.73
     judgments
    0.72
     appreciation
    0.72
    uably
    0.71
     asset
    0.69
    Activations Density 0.031%

    No Known Activations