© 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 3072
    9. 8-RES_FS3072-JB
    11. 2961
    Prev
    Next
    INDEX
    Explanations

    details related to crimes, police investigations, and personal relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    309
    +0.11
    0.5%
    121
    +0.10
    0.5%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.09
    318
    +0.10
    0.08
    350
    +0.10
    0.07
    Negative Logits
     takedown
    -0.86
    pmwiki
    -0.86
     captcha
    -0.79
     metrics
    -0.78
    ibaba
    -0.74
     LEVEL
    -0.73
    Weapon
    -0.71
     inacc
    -0.71
     projectiles
    -0.69
     replay
    -0.68
    POSITIVE LOGITS
     daughter
    1.56
     daughters
    1.49
     grandchildren
    1.46
     eldest
    1.41
     granddaughter
    1.40
     grandparents
    1.33
     siblings
    1.31
     grandmother
    1.28
     aunt
    1.27
    daughter
    1.27
    Activations Density 2.686%

    No Known Activations