© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10775
    Prev
    Next
    INDEX
    Explanations

    numerical values such as numbers, percentages, and measurements within text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.57
    2.0%
    362
    +0.22
    0.8%
    608
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.57
    0.36
    393
    +0.22
    0.30
    385
    +0.19
    0.31
    Negative Logits
    âĢł
    -1.01
    zon
    -0.98
    tackle
    -0.94
     Albania
    -0.92
    ãĥ»
    -0.91
    rand
    -0.91
    ãĤ´
    -0.90
    ea
    -0.90
     besides
    -0.90
    âĿ
    -0.87
    POSITIVE LOGITS
     slightest
    2.00
     usual
    1.94
     same
    1.67
     aforementioned
    1.65
     entirety
    1.64
     smallest
    1.57
     rest
    1.54
     entire
    1.51
     simplest
    1.50
     latter
    1.50
    Activations Density 4.977%

    No Known Activations