© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    topics related to economic factors, particularly focusing on interest rates, asset prices, and market trends

    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
    +0.18
    1.0%
    393
    +0.12
    0.7%
    321
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.32
    362
    +0.12
    0.15
    640
    +0.09
    0.25
    Negative Logits
    istar
    -0.80
    uthor
    -0.79
    ulhu
    -0.68
    abre
    -0.64
    IJ
    -0.63
    clerosis
    -0.62
    alysis
    -0.61
    iry
    -0.61
    heastern
    -0.61
    opsy
    -0.60
    POSITIVE LOGITS
     goods
    0.90
     groceries
    0.79
     commodities
    0.75
     tickets
    0.74
     CDs
    0.70
     coins
    0.69
     merchandise
    0.69
     grapes
    0.68
     bitcoins
    0.67
     books
    0.67
    Activations Density 13.343%

    No Known Activations