© 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. 5810
    Prev
    Next
    INDEX
    Explanations

    information related to electric power systems and components like batteries, power control units, and energy consumption

    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
    +0.20
    0.6%
    18
    +0.15
    0.5%
    150
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.20
    0.04
    523
    +0.15
    0.05
    755
    +0.14
    0.04
    Negative Logits
     Von
    -1.21
    ean
    -1.09
    erella
    -1.03
    ead
    -1.00
     Suc
    -0.98
    roit
    -0.96
    ript
    -0.95
    ordan
    -0.94
     Debor
    -0.94
    ãģĵ
    -0.93
    POSITIVE LOGITS
    houses
    1.54
    train
    1.32
    plant
    1.30
    boats
    1.27
     outage
    1.24
     stations
    1.20
    lifting
    1.19
    stroke
    1.17
    station
    1.13
    wash
    1.10
    Activations Density 0.539%

    No Known Activations