© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    terms related to the Russia-Ukraine conflict and Crimea, such as names of locations, political figures, military terms, and economic actions

    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
    339
    +0.09
    0.5%
    755
    +0.09
    0.5%
    651
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.29
    326
    +0.09
    0.26
    220
    +0.09
    0.10
    Negative Logits
    ality
    -0.78
    ship
    -0.77
    isco
    -0.76
    ently
    -0.75
    ally
    -0.71
    als
    -0.70
    entially
    -0.70
    encing
    -0.66
    ienne
    -0.65
    ships
    -0.65
    POSITIVE LOGITS
     Cookie
    0.53
     Rite
    0.49
     Bulk
    0.49
     Ones
    0.49
    EStream
    0.48
     Alban
    0.48
     Jenner
    0.48
    FTWARE
    0.46
     Cookies
    0.46
    illard
    0.46
    Activations Density 9.271%

    No Known Activations