© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13643
    Prev
    Next
    INDEX
    Explanations

    the word "live" as it relates to various contexts such as living with medical conditions, freely, in the moment, in a community, and through different life stages and experiences

    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
    132
    +0.18
    0.6%
    70
    +0.17
    0.6%
    570
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.18
    0.07
    759
    +0.17
    0.05
    132
    +0.16
    0.05
    Negative Logits
    enei
    -1.21
    essee
    -1.20
    notation
    -1.10
    sonian
    -1.09
    aneers
    -1.08
    umin
    -1.08
    ippi
    -1.05
    elight
    -1.05
    iban
    -1.04
    reg
    -1.04
    POSITIVE LOGITS
     vic
    1.11
    lihood
    1.07
    liness
    1.06
    lier
    1.01
     happily
    0.96
     Forever
    0.93
     Reincarn
    0.93
    makers
    0.93
    stead
    0.93
     breathing
    0.90
    Activations Density 0.517%

    No Known Activations