© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2649
    Prev
    Next
    INDEX
    Explanations

    phrases related to caregiving or taking care of others

    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
    288
    +0.21
    0.9%
    679
    +0.13
    0.6%
    459
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.19
    575
    +0.13
    0.14
    388
    +0.12
    0.11
    Negative Logits
     Marketable
    -0.97
    */(
    -0.95
    ãģĦ
    -0.86
    ãĥĥãĥī
    -0.84
    thin
    -0.73
    lihood
    -0.72
    chrom
    -0.71
    ãģį
    -0.70
    ordan
    -0.70
    cloud
    -0.69
    POSITIVE LOGITS
     operated
    1.07
     staffed
    1.03
     located
    1.03
     premises
    1.00
    inery
    0.93
     facilities
    0.92
    esan
    0.90
     facility
    0.89
     operator
    0.87
     frequ
    0.86
    Activations Density 3.032%

    No Known Activations