© 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. 12874
    Prev
    Next
    INDEX
    Explanations

    terms related to international conflicts 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
    276
    +0.15
    0.6%
    706
    +0.15
    0.6%
    0
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    -0.01
    276
    +0.15
    0.10
    749
    +0.14
    0.07
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -1.05
     needles
    -0.96
     straw
    -0.87
     spears
    -0.86
     Halls
    -0.85
     Twain
    -0.83
     strawberries
    -0.83
     caves
    -0.82
     bedrooms
    -0.81
     Brooks
    -0.80
    POSITIVE LOGITS
    blems
    1.63
    ceed
    1.57
    digy
    1.57
    secut
    1.51
    secution
    1.43
    posal
    1.41
    spect
    1.39
    gressive
    1.36
    gression
    1.34
    hibited
    1.31
    Activations Density 5.357%

    No Known Activations