© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 37171
    Prev
    Next
    INDEX
    Explanations

    information related to age comparison, particularly focusing on the older age group

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    0.9%
    288
    +0.14
    0.5%
    132
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.24
    0.08
    726
    +0.14
    0.08
    156
    +0.14
    0.06
    Negative Logits
    edIn
    -0.94
    utterstock
    -0.93
    odor
    -0.91
    xtap
    -0.90
    ãĥ£
    -0.89
    otion
    -0.86
    orial
    -0.82
    trak
    -0.80
    ayne
    -0.80
    alion
    -0.80
    POSITIVE LOGITS
     sibling
    1.18
     than
    1.17
     generations
    1.16
     versions
    1.15
     sister
    1.11
     Than
    1.06
     fashioned
    1.05
    than
    1.04
     brother
    1.01
     siblings
    0.94
    Activations Density 5.481%

    No Known Activations