© 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. 18829
    Prev
    Next
    INDEX
    Explanations

    phrases related to tracking or surveillance

    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
    418
    +0.10
    0.4%
    218
    +0.09
    0.4%
    468
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    622
    +0.10
    0.01
    691
    +0.09
    0.01
    418
    +0.09
    0.01
    Negative Logits
    ahu
    -0.71
    osi
    -0.64
    annis
    -0.62
    osate
    -0.60
     Prelude
    -0.60
    acco
    -0.60
     Harbor
    -0.59
    sbm
    -0.58
     spons
    -0.58
    ansk
    -0.57
    POSITIVE LOGITS
    itored
    0.80
    gers
    0.79
    suit
    0.74
    suits
    0.73
     Tracks
    0.73
    gered
    0.73
     tracks
    0.71
    record
    0.70
    illance
    0.70
    oleon
    0.69
    Activations Density 0.026%

    No Known Activations