© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and development activities, especially focusing on funding, military research, and scientific endeavors

    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
    +0.27
    0.9%
    679
    +0.18
    0.6%
    360
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.27
    0.05
    524
    +0.18
    0.05
    575
    +0.18
    0.05
    Negative Logits
     Ukrain
    -0.90
    emonic
    -0.90
    erest
    -0.89
     dism
    -0.88
    anza
    -0.88
     waving
    -0.87
     Swap
    -0.86
    ĪĴ
    -0.86
    cakes
    -0.85
     gent
    -0.85
    POSITIVE LOGITS
    çīĪ
    1.18
     labs
    1.15
     laboratories
    1.13
    sonian
    1.12
     scientist
    1.09
     Scientist
    1.06
    yssey
    1.05
    rador
    1.02
    sts
    1.01
     assistants
    1.01
    Activations Density 0.526%

    No Known Activations