© 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. 1545
    Prev
    Next
    INDEX
    Explanations

    information related to search engine optimization (SEO), including keywords such as "SEO professionals," "SEO Book," and "organic search traffic."

    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
    167
    +0.13
    0.5%
    447
    +0.12
    0.5%
    649
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.20
    575
    +0.12
    0.15
    247
    +0.11
    0.09
    Negative Logits
    SPONSORED
    -0.81
    enegger
    -0.80
     militias
    -0.74
    emption
    -0.73
     Kham
    -0.71
    lain
    -0.70
    emis
    -0.70
    ports
    -0.69
     smuggled
    -0.69
     relics
    -0.69
    POSITIVE LOGITS
    ogle
    0.80
    ĺħ
    0.74
     Anxiety
    0.74
     encount
    0.74
    reprene
    0.72
     answ
    0.72
     etiquette
    0.72
    stress
    0.72
     invitation
    0.71
     beginner
    0.71
    Activations Density 3.343%

    No Known Activations