© 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. 32707
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic growth and related indicators

    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
    +0.26
    1.2%
    216
    +0.15
    0.7%
    288
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.26
    0.08
    375
    +0.15
    0.04
    97
    +0.15
    0.04
    Negative Logits
    nee
    -1.01
    ãĥīãĥ©
    -0.80
    WARE
    -0.77
    cknowled
    -0.77
    CLA
    -0.77
    pper
    -0.75
    POS
    -0.75
    rol
    -0.74
    opol
    -0.72
    nery
    -0.72
    POSITIVE LOGITS
     promot
    0.93
    rates
    0.92
     rates
    0.87
     prospects
    0.85
     growth
    0.82
     Rates
    0.81
    acious
    0.78
     rate
    0.78
     promotion
    0.78
     Growth
    0.77
    Activations Density 9.109%

    No Known Activations