Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 746
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the need or requirement for something to be done

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    551
    +0.14
    0.6%
    49
    +0.10
    0.5%
    24
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.14
    0.11
    49
    +0.10
    0.10
    105
    +0.10
    0.08
    Negative Logits
    vironment
    -0.70
    Recommended
    -0.68
     Emerging
    -0.67
     Globe
    -0.67
     Lambert
    -0.64
     Onion
    -0.63
     Rust
    -0.62
     Guilty
    -0.61
    Mur
    -0.59
     Nort
    -0.58
    POSITIVE LOGITS
     rely
    1.16
     wait
    1.10
     endure
    1.08
     contend
    1.05
     abide
    1.04
     obey
    1.01
     undergo
    1.00
     reckon
    1.00
     fend
    0.99
     rethink
    0.99
    Activations Density 0.981%

    No Known Activations