© 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 Local
    9. 6-RES_SCL-AJT
    11. 33189
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying informed and up to date on various topics

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.11
    0.6%
    388
    +0.09
    0.5%
    710
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.31
    393
    +0.09
    0.32
    270
    +0.08
    0.05
    Negative Logits
    alties
    -0.63
    ĸļ
    -0.62
    amiya
    -0.61
    interstitial
    -0.59
    ylum
    -0.58
    inals
    -0.57
    ipal
    -0.55
    phy
    -0.54
    iyah
    -0.53
    ulla
    -0.53
    POSITIVE LOGITS
     updates
    0.73
     developments
    0.71
     Updates
    0.70
     information
    0.68
     notifications
    0.64
     INFORMATION
    0.60
     whereabouts
    0.60
     info
    0.59
     tid
    0.58
    izoph
    0.58
    Activations Density 16.781%

    No Known Activations