© 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
    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. 35261
    Prev
    Next
    INDEX
    Explanations

    last minute events or activities

    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
    +0.11
    0.7%
    381
    +0.08
    0.5%
    765
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.11
    0.07
    132
    +0.08
    0.06
    709
    +0.07
    0.09
    Negative Logits
    WAR
    -0.66
    MAT
    -0.57
    Rust
    -0.53
     Mothers
    -0.52
    wine
    -0.52
    avia
    -0.51
    ashtra
    -0.51
    letes
    -0.51
    LLOW
    -0.50
    odd
    -0.50
    POSITIVE LOGITS
     scramble
    0.58
    aneously
    0.55
     cancell
    0.54
     sequencing
    0.54
     preparations
    0.53
     ambush
    0.51
     disposal
    0.50
     maneuver
    0.50
    imester
    0.50
     bunker
    0.49
    Activations Density 7.048%

    No Known Activations