© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32470
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and construction

    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
    +0.28
    1.7%
    393
    +0.10
    0.6%
    718
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.28
    0.37
    138
    +0.10
    0.35
    64
    +0.10
    -0.22
    Negative Logits
     Perspective
    -0.45
     Directions
    -0.45
     glances
    -0.45
    drawn
    -0.45
     fireworks
    -0.44
     screenshots
    -0.44
    calling
    -0.43
    listed
    -0.42
    comments
    -0.41
     Premiership
    -0.41
    POSITIVE LOGITS
     accommodate
    0.94
     withstand
    0.93
    ggles
    0.83
     emulate
    0.82
     cope
    0.82
     satisfy
    0.82
     maximize
    0.81
     survive
    0.80
     compensate
    0.80
     provide
    0.79
    Activations Density 12.990%

    No Known Activations