© 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 12288
    9. 8-RES_FS12288-JB
    11. 644
    Prev
    Next
    INDEX
    Explanations

    words related to underlying issues or problems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    380
    +0.12
    0.5%
    284
    +0.11
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.12
    0.07
    362
    +0.11
    0.06
    284
    +0.10
    0.05
    Negative Logits
    osponsors
    -0.98
    airs
    -0.92
    quer
    -0.86
    ateurs
    -0.85
    earch
    -0.85
    ooters
    -0.82
    hops
    -0.81
    ittees
    -0.80
    paio
    -0.80
    ooter
    -0.79
    POSITIVE LOGITS
     belief
    1.39
     assumption
    1.31
     societal
    1.21
     notion
    1.20
     principle
    1.20
     beliefs
    1.18
     misconception
    1.18
     philosophical
    1.16
     ideological
    1.16
     psychological
    1.15
    Activations Density 0.386%

    No Known Activations