© 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. 11127
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an overall or complete context

    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
    344
    +0.17
    0.6%
    59
    +0.16
    0.5%
    497
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.17
    0.05
    700
    +0.16
    0.04
    632
    +0.14
    0.04
    Negative Logits
     advoc
    -1.15
    ju
    -1.09
    ker
    -0.98
    KER
    -0.97
    Ju
    -0.92
    akers
    -0.92
    jo
    -0.91
    lict
    -0.85
    zy
    -0.84
    Adv
    -0.82
    POSITIVE LOGITS
    ength
    1.13
    hearted
    1.12
    heartedly
    1.11
     length
    1.04
     spectrum
    1.01
     gam
    0.99
     ordeal
    0.94
     freaking
    0.92
    assetsadobe
    0.91
     contents
    0.89
    Activations Density 0.360%

    No Known Activations