© 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 Local
    9. 6-RES_SCL-AJT
    11. 14284
    Prev
    Next
    INDEX
    Explanations

    phrases related to international affairs and politics

    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
    480
    +0.34
    3.5%
    87
    +0.29
    3.0%
    447
    +0.24
    2.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.34
    0.12
    266
    +0.29
    0.50
    288
    +0.24
    0.45
    Negative Logits
    Ô
    -0.28
    -0.27
     Bayer
    -0.26
    actionDate
    -0.25
    bestos
    -0.24
    -0.23
     Slav
    -0.22
    Money
    -0.22
    Ñı
    -0.22
     Undead
    -0.22
    POSITIVE LOGITS
     rul
    0.29
     wat
    0.26
    pedia
    0.24
    anship
    0.24
    gate
    0.24
     shenanigans
    0.24
    watching
    0.23
    ahime
    0.22
     woes
    0.22
     itself
    0.22
    Activations Density 25.120%

    No Known Activations