© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5669
    Prev
    Next
    INDEX
    Explanations

    instances of words related to methods or choices, especially related to procedures for selection

    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
    288
    +0.23
    0.8%
    726
    +0.17
    0.5%
    679
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.23
    0.04
    288
    +0.17
    0.06
    222
    +0.16
    0.04
    Negative Logits
    olid
    -1.08
    loo
    -1.00
    wig
    -0.97
    BIP
    -0.94
    peria
    -0.93
    kos
    -0.93
    Sea
    -0.92
    ijk
    -0.89
    here
    -0.89
    bley
    -0.89
    POSITIVE LOGITS
    ivity
    1.36
    selection
    1.30
    ively
    1.27
     criteria
    1.20
     selections
    1.10
    dinand
    1.08
    axe
    1.04
    cuts
    1.04
    picked
    1.02
     Assass
    1.01
    Activations Density 0.618%

    No Known Activations