© 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 EvalsExportsinterp-engineNEWAPI 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. 36588
    Prev
    Next
    INDEX
    Explanations

    concepts related to economics and business practices

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.17
    1.7%
    64
    +0.16
    1.5%
    756
    +0.15
    1.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.17
    -0.08
    87
    +0.16
    -0.08
    570
    +0.15
    0.07
    Negative Logits
    çīĪ
    -0.40
     Journalism
    -0.38
     Podcast
    -0.31
     Blog
    -0.31
     acron
    -0.31
    podcast
    -0.30
    âĢİ
    -0.30
     Cities
    -0.30
     Hogan
    -0.29
     satirical
    -0.29
    POSITIVE LOGITS
     downstream
    0.43
     undet
    0.41
     predetermined
    0.39
     desired
    0.37
     whichever
    0.36
     advantageous
    0.36
     thereby
    0.36
     depending
    0.35
     desirable
    0.34
     oneself
    0.34
    Activations Density 9.985%

    No Known Activations