© 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. 12864
    Prev
    Next
    INDEX
    Explanations

    words related to legal rights and entitlements

    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
    385
    +0.16
    0.5%
    104
    +0.15
    0.5%
    393
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.16
    0.05
    228
    +0.15
    0.04
    425
    +0.15
    0.04
    Negative Logits
    UF
    -1.22
    bilt
    -0.99
    hran
    -0.95
    soDeliveryDate
    -0.94
    beta
    -0.92
    cephal
    -0.91
    breaks
    -0.90
    heads
    -0.89
    ripp
    -0.88
    nets
    -0.87
    POSITIVE LOGITS
     redress
    1.17
    ignty
    1.13
     Privacy
    1.03
     Rights
    1.02
     revenge
    0.99
     freedom
    0.99
    ario
    0.98
     roam
    0.97
     hers
    0.96
     act
    0.95
    Activations Density 0.636%

    No Known Activations