© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 792
    Prev
    Next
    INDEX
    Explanations

    Greek-related terms and financial/economic terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    718
    +0.15
    0.6%
    289
    +0.13
    0.5%
    546
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.12
    326
    +0.13
    0.09
    57
    +0.12
    0.06
    Negative Logits
    eer
    -1.27
    eers
    -1.13
    DERR
    -1.11
    ividual
    -1.01
    osterone
    -0.99
    bsp
    -0.95
    eal
    -0.95
    een
    -0.94
    ooth
    -0.94
    ookie
    -0.94
    POSITIVE LOGITS
     traged
    1.08
     Freak
    1.00
     Syri
    0.95
     Athens
    0.95
     Greece
    0.94
    aea
    0.92
     Greek
    0.91
     Greeks
    0.89
     yogurt
    0.84
     Chrys
    0.83
    Activations Density 1.746%

    No Known Activations