© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14535
    Prev
    Next
    INDEX
    Explanations

    instances of the word "luck" or related concepts

    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
    674
    +0.10
    0.5%
    449
    +0.08
    0.4%
    139
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.10
    0.01
    8
    +0.08
    0.02
    239
    +0.08
    0.01
    Negative Logits
    heid
    -0.62
    INGS
    -0.52
     Detention
    -0.48
    ury
    -0.47
     USE
    -0.47
    atives
    -0.47
    åĤ
    -0.46
    edom
    -0.46
    intent
    -0.45
     reckoning
    -0.45
    POSITIVE LOGITS
    nown
    0.77
    yrinth
    0.64
    ansson
    0.63
     fate
    0.58
    anos
    0.57
     Mara
    0.57
    hedon
    0.55
    NPR
    0.54
    chron
    0.54
    Pand
    0.54
    Activations Density 0.049%

    No Known Activations