© 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. 14690
    Prev
    Next
    INDEX
    Explanations

    dates formatted in year-month-day and mentions of different telecommunication companies and services

    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
    363
    +0.14
    0.5%
    440
    +0.14
    0.5%
    29
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.03
    505
    +0.14
    0.02
    398
    +0.14
    0.02
    Negative Logits
    TPPStreamerBot
    -1.16
    avorite
    -1.15
    itionally
    -1.11
    ixel
    -1.06
    ierrez
    -1.05
    soDeliveryDate
    -1.03
    uyomi
    -1.01
     unloaded
    -0.96
    hops
    -0.93
    anyahu
    -0.93
    POSITIVE LOGITS
    76561
    1.20
    Posts
    1.15
     Payments
    1.01
    Internet
    1.00
    âĸ¬
    1.00
     1918
    0.97
    Member
    0.94
    payer
    0.93
    ãĥİ
    0.93
     Banking
    0.92
    Activations Density 0.126%

    No Known Activations