© 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. 13986
    Prev
    Next
    INDEX
    Explanations

    words related to monetary policy, financial institutions, and economic systems

    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
    288
    +0.14
    0.7%
    447
    +0.10
    0.5%
    502
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.18
    707
    +0.10
    0.09
    444
    +0.09
    0.06
    Negative Logits
    20439
    -0.78
    IVERS
    -0.72
    bleacher
    -0.71
    lam
    -0.71
    nel
    -0.69
     Tomato
    -0.67
    nen
    -0.67
    ELS
    -0.67
    lain
    -0.66
    uous
    -0.65
    POSITIVE LOGITS
     easing
    0.86
    ized
    0.78
    ization
    0.77
     denomination
    0.76
     union
    0.75
     interventions
    0.75
     punishment
    0.74
     currency
    0.74
     fluctuations
    0.74
     inflation
    0.74
    Activations Density 5.213%

    No Known Activations