© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer system performance and optimization

    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
    326
    +0.21
    0.6%
    566
    +0.16
    0.5%
    743
    +0.15
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.14
    659
    +0.16
    0.15
    57
    +0.15
    0.12
    Negative Logits
     Samoa
    -1.16
    uyomi
    -1.15
    sburgh
    -1.10
    andowski
    -1.09
    iasis
    -1.08
    hold
    -1.03
    idate
    -1.02
     Emir
    -1.01
     Telegram
    -1.01
     Notting
    -1.01
    POSITIVE LOGITS
    BC
    1.96
    RC
    1.90
    OC
    1.90
    TF
    1.90
    OST
    1.84
    ONY
    1.84
    RA
    1.83
    FP
    1.83
    SS
    1.83
    IM
    1.81
    Activations Density 3.368%

    No Known Activations