© 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
    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. 4848
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, specifically focusing on AMD's Zen architecture and associated products

    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
    659
    +0.11
    0.6%
    526
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.20
    613
    +0.10
    0.08
    288
    +0.10
    0.18
    Negative Logits
     Lauder
    -0.69
    riers
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
    à¤
    -0.62
     Bagg
    -0.62
     Tire
    -0.61
     Mississ
    -0.59
    IRD
    -0.59
    Ø©
    -0.58
     Tolkien
    -0.58
    POSITIVE LOGITS
    eca
    0.99
    obia
    0.90
    zen
    0.83
    ith
    0.82
    itized
    0.82
    ical
    0.81
    geist
    0.80
    emy
    0.80
    jet
    0.76
    ica
    0.75
    Activations Density 7.199%

    No Known Activations