© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13159
    Prev
    Next
    INDEX
    Explanations

    sentences containing technical terms and details related to data organization and information systems

    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
    75
    +0.11
    0.4%
    558
    +0.11
    0.4%
    692
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.11
    0.09
    665
    +0.11
    0.10
    279
    +0.10
    0.08
    Negative Logits
    nir
    -0.93
    bringer
    -0.88
    wake
    -0.84
    sm
    -0.81
    alm
    -0.81
    ull
    -0.80
    insky
    -0.79
    nu
    -0.79
    death
    -0.78
    sn
    -0.77
    POSITIVE LOGITS
     everything
    1.03
    uggest
    0.92
     coordinates
    0.87
    ufact
    0.87
     summar
    0.81
    :]
    0.77
     links
    0.76
     redundant
    0.75
    yrinth
    0.74
     navigation
    0.73
    Activations Density 2.841%

    No Known Activations