© 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 Local
    9. 6-RES_SCL-AJT
    11. 33956
    Prev
    Next
    INDEX
    Explanations

    phrases related to international aid and disaster relief efforts

    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
    447
    +0.28
    1.3%
    679
    +0.15
    0.7%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.16
    679
    +0.15
    0.13
    531
    +0.11
    0.06
    Negative Logits
     Beard
    -0.87
    beard
    -0.72
     Bellev
    -0.68
     Schne
    -0.67
    theless
    -0.65
    âĸ¬
    -0.64
    nen
    -0.63
     Hots
    -0.63
    agall
    -0.62
    arella
    -0.61
    POSITIVE LOGITS
     aid
    0.98
    giving
    0.86
     worker
    0.75
     recip
    0.72
    aments
    0.71
     supplies
    0.71
     repatri
    0.70
    fulness
    0.70
    abil
    0.69
    iliate
    0.69
    Activations Density 4.254%

    No Known Activations