© 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. 32699
    Prev
    Next
    INDEX
    Explanations

    terms related to central banking, monetary policy, and interest rates

    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
    +0.20
    0.8%
    288
    +0.15
    0.6%
    146
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.20
    0.09
    617
    +0.15
    0.06
    241
    +0.14
    0.06
    Negative Logits
     Tolkien
    -0.83
    Ô
    -0.81
     Mehran
    -0.80
     Faw
    -0.79
     Sora
    -0.79
     Bucc
    -0.78
    lihood
    -0.77
     Surviv
    -0.75
     Bram
    -0.75
     Klingon
    -0.73
    POSITIVE LOGITS
    ollar
    1.19
    ERAL
    1.10
    erer
    0.99
    erity
    0.97
    eli
    0.89
    wire
    0.89
    liction
    0.89
     Reserve
    0.88
     bulls
    0.87
    ered
    0.87
    Activations Density 5.284%

    No Known Activations