© 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. 40539
    Prev
    Next
    INDEX
    Explanations

    information related to international alliances and relationships

    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
    +0.27
    1.5%
    288
    +0.14
    0.7%
    679
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.27
    0.14
    608
    +0.14
    0.19
    385
    +0.12
    0.15
    Negative Logits
    SpaceEngineers
    -0.69
    nit
    -0.66
    plet
    -0.65
    iday
    -0.65
    ²¾
    -0.64
    aul
    -0.64
    acco
    -0.61
    nutrition
    -0.60
    ifax
    -0.59
    teen
    -0.59
    POSITIVE LOGITS
     Allies
    0.72
     ally
    0.65
     allies
    0.65
     allied
    0.64
     flank
    0.61
     Ally
    0.60
     milit
    0.57
     colleague
    0.57
     chorus
    0.56
    illary
    0.56
    Activations Density 10.104%

    No Known Activations