© 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. 14000
    Prev
    Next
    INDEX
    Explanations

    words related to influential political figures, particularly focusing on the Reagan administration

    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
    +0.21
    1.0%
    288
    +0.17
    0.8%
    385
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.17
    414
    +0.17
    0.07
    709
    +0.13
    0.10
    Negative Logits
    tered
    -0.70
    hemat
    -0.67
    enance
    -0.65
    ĨĴ
    -0.65
    ļ
    -0.63
    âĸ¬âĸ¬
    -0.62
    ournals
    -0.60
     Malays
    -0.60
    ħ
    -0.58
    ¤
    -0.58
    POSITIVE LOGITS
    omics
    1.15
     Reagan
    0.88
    eland
    0.73
    ites
    0.71
    overs
    0.70
     Schwarzenegger
    0.70
    aldo
    0.69
    ettes
    0.67
    ism
    0.67
    itures
    0.67
    Activations Density 5.012%

    No Known Activations