© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32611
    Prev
    Next
    INDEX
    Explanations

    vegetarian and baking ingredients, particularly eggs

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    99
    +0.16
    0.6%
    447
    +0.15
    0.6%
    647
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.16
    -0.03
    316
    +0.15
    0.07
    99
    +0.15
    0.07
    Negative Logits
     Vu
    -0.85
    ESS
    -0.84
    SPONSORED
    -0.80
     McKenna
    -0.78
    raints
    -0.76
     Lumpur
    -0.75
     Fiction
    -0.72
     Colleges
    -0.71
    姫
    -0.70
    orts
    -0.70
    POSITIVE LOGITS
    shell
    1.47
    cellent
    1.40
    plant
    1.33
     hatched
    1.01
     eggs
    0.96
     egg
    0.94
     Eggs
    0.90
    ster
    0.85
    weed
    0.84
    meal
    0.83
    Activations Density 5.372%

    No Known Activations