© 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. 974
    Prev
    Next
    INDEX
    Explanations

    details about economic and political actions related to trade agreements and government policies

    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
    679
    +0.18
    1.1%
    640
    +0.13
    0.8%
    393
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.33
    640
    +0.13
    0.34
    679
    +0.09
    0.34
    Negative Logits
     disemb
    -0.67
     deity
    -0.65
    clus
    -0.62
     unden
    -0.60
     masculine
    -0.60
     spoiler
    -0.60
    ãĤ¨ãĥ«
    -0.59
     muse
    -0.58
     cavern
    -0.57
     erotic
    -0.56
    POSITIVE LOGITS
     Meanwhile
    0.93
     Similarly
    0.93
     Likewise
    0.88
     Moreover
    0.87
     Others
    0.85
     Additionally
    0.84
     Consequently
    0.84
     Furthermore
    0.83
     Conversely
    0.83
     Ironically
    0.82
    Activations Density 7.076%

    No Known Activations