© 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. 2969
    Prev
    Next
    INDEX
    Explanations

    authors talking about economic indicators such as "net migration," "net neutrality," and "net worth."

    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
    712
    +0.10
    0.5%
    699
    +0.10
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.04
    288
    +0.10
    0.05
    699
    +0.10
    0.03
    Negative Logits
     Templ
    -0.67
     Barcl
    -0.66
     unres
    -0.64
    hips
    -0.62
    auga
    -0.62
     Dup
    -0.62
     Styles
    -0.62
     Pend
    -0.60
     Flask
    -0.60
    odied
    -0.59
    POSITIVE LOGITS
    anyahu
    1.58
    izens
    1.52
    izen
    1.42
    tle
    1.28
    flix
    1.16
    her
    1.14
    hers
    1.12
    working
    1.10
     neutrality
    1.06
    ting
    1.06
    Activations Density 0.583%

    No Known Activations