© 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 49152
    9. 8-RES_FS49152-JB
    11. 26513
    Prev
    Next
    INDEX
    Explanations

    mentions of social media engagement or interaction

    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
    32
    +0.12
    0.5%
    431
    +0.11
    0.5%
    172
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.12
    0.02
    74
    +0.11
    0.01
    583
    +0.10
    0.01
    Negative Logits
     laun
    -0.65
    issance
    -0.64
    quest
    -0.64
     restitution
    -0.64
     Dres
    -0.61
     conclud
    -0.60
     wom
    -0.60
     satisf
    -0.60
    ARDIS
    -0.59
     omission
    -0.59
    POSITIVE LOGITS
     Subscribe
    0.90
    facebook
    0.88
     FACE
    0.87
     guiActive
    0.85
     facebook
    0.79
    Subscribe
    0.78
     Alive
    0.77
    edin
    0.76
    Comments
    0.75
    iframe
    0.75
    Activations Density 0.025%

    No Known Activations