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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13519
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions related to cooking and baking recipes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: Local cluster above bottom line touching e2e-recon cluster - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.29
    1.6%
    447
    +0.24
    1.3%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.46
    6
    +0.24
    0.34
    255
    +0.11
    0.22
    Negative Logits
     affili
    -0.80
     unexplained
    -0.75
     affiliated
    -0.74
     indebted
    -0.71
     estranged
    -0.69
     affiliation
    -0.67
    terday
    -0.67
     anomal
    -0.66
     underage
    -0.64
     royalty
    -0.64
    POSITIVE LOGITS
     Then
    0.99
    Then
    0.95
    Alternatively
    0.91
    Remove
    0.90
     Afterwards
    0.90
     Slowly
    0.90
    Once
    0.89
     Ideally
    0.89
    Optional
    0.88
     Depending
    0.87
    Activations Density 13.216%

    No Known Activations