© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3254
    Prev
    Next
    INDEX
    Explanations

    references to "CB," which likely stands for "central business" or "central bank" based on the context involving economic and financial topics

    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
    146
    +0.11
    0.5%
    314
    +0.11
    0.5%
    187
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.06
    628
    +0.11
    0.04
    288
    +0.11
    0.07
    Negative Logits
    wine
    -0.74
    umerable
    -0.74
     Gutenberg
    -0.73
     CMS
    -0.71
     Bundes
    -0.71
    cry
    -0.70
     Gors
    -0.68
     vein
    -0.68
    lihood
    -0.68
     pend
    -0.68
    POSITIVE LOGITS
    dar
    0.89
    anut
    0.85
    stocks
    0.85
    aret
    0.82
    arest
    0.81
    enzie
    0.80
    rief
    0.78
    illion
    0.77
    shaw
    0.76
    oard
    0.76
    Activations Density 0.671%

    No Known Activations