© 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. 32791
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and equations

    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
    +0.26
    1.1%
    156
    +0.12
    0.5%
    678
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.26
    0.15
    678
    +0.12
    0.08
    738
    +0.12
    0.05
    Negative Logits
     whistlebl
    -0.94
     seiz
    -0.82
    ESH
    -0.76
     adrenaline
    -0.75
    Mobile
    -0.74
     grassroots
    -0.74
    laun
    -0.73
    assion
    -0.72
     surges
    -0.72
     Kuwait
    -0.71
    POSITIVE LOGITS
     theorem
    1.42
     \(
    1.30
     \(\
    1.30
     algebra
    1.20
     $\
    1.18
     Mathemat
    1.15
     integers
    1.13
     mathematic
    1.09
     equations
    1.08
     coefficients
    1.07
    Activations Density 22.130%

    No Known Activations