© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    biochemical laboratory procedures and techniques

    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
    447
    +0.27
    1.1%
    150
    +0.13
    0.5%
    378
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.32
    640
    +0.13
    0.28
    739
    +0.12
    0.05
    Negative Logits
    soDeliveryDate
    -0.99
    SPONSORED
    -0.88
    estate
    -0.83
    think
    -0.82
     Sovere
    -0.80
    inventoryQuantity
    -0.78
     Tant
    -0.78
    quickShipAvailable
    -0.76
    doesn
    -0.75
    uably
    -0.75
    POSITIVE LOGITS
    alyses
    0.99
     validated
    0.98
     randomized
    0.93
     Kaplan
    0.92
     Procedures
    0.87
     analyses
    0.85
     manually
    0.85
    ETHOD
    0.83
     procedure
    0.83
     assay
    0.82
    Activations Density 16.388%

    No Known Activations