© 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 Local
    5. 6-RES_SCL-AJT
    6. 4954
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sun or solar-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    172
    +0.12
    0.6%
    687
    +0.10
    0.5%
    406
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.30
    630
    +0.10
    0.09
    264
    +0.09
    0.04
    Negative Logits
    */(
    -0.73
    é¾įå
    -0.69
    ierre
    -0.66
    actionDate
    -0.63
    vernment
    -0.62
    leneck
    -0.62
    reau
    -0.58
     guiIcon
    -0.57
    :{
    -0.57
     Marketable
    -0.57
    POSITIVE LOGITS
     Rays
    0.74
    onday
    0.68
     Predators
    0.65
    wake
    0.63
    nova
    0.62
     gloom
    0.62
     nights
    0.61
    ibaba
    0.61
    ioxide
    0.61
     Pis
    0.60
    Activations Density 16.828%

    No Known Activations