© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13829
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions, arguments, and debates

    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
    +0.16
    0.6%
    247
    +0.14
    0.5%
    642
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.14
    745
    +0.14
    -0.08
    97
    +0.12
    0.05
    Negative Logits
     Gorge
    -0.87
     Adin
    -0.81
     Gap
    -0.79
    anus
    -0.79
    raltar
    -0.75
    sis
    -0.74
    den
    -0.73
     Journals
    -0.73
    ı
    -0.73
     Brist
    -0.72
    POSITIVE LOGITS
    itism
    1.75
    ably
    1.03
    ited
    1.02
    eering
    0.92
    ability
    0.90
    hift
    0.90
    naire
    0.90
    ative
    0.90
    uate
    0.88
    atives
    0.88
    Activations Density 5.778%

    No Known Activations