© 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. 4678
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" in the text, and specifically focuses on sentences where "or" is adjacent to other words

    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
    +0.19
    0.7%
    393
    +0.14
    0.5%
    225
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.25
    578
    +0.14
    0.05
    284
    +0.13
    0.10
    Negative Logits
     Pony
    -1.05
    ocracy
    -0.94
    ulhu
    -0.89
    ocrats
    -0.89
    ocrat
    -0.88
    ETS
    -0.83
    ascus
    -0.82
     Examiner
    -0.81
    achine
    -0.80
     Sorce
    -0.79
    POSITIVE LOGITS
    acles
    1.52
    nam
    1.50
    acle
    1.50
    Else
    1.47
    chard
    1.45
    ifice
    1.45
    nery
    1.37
    chid
    1.36
     otherwise
    1.28
    atory
    1.20
    Activations Density 12.408%

    No Known Activations