© 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. 34020
    Prev
    Next
    INDEX
    Explanations

    mentions of chocolate and dessert-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
    447
    +0.22
    1.0%
    288
    +0.18
    0.8%
    326
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.22
    0.09
    675
    +0.18
    0.10
    623
    +0.12
    0.05
    Negative Logits
    atives
    -0.86
    WARD
    -0.82
    umbnail
    -0.73
    kus
    -0.72
    ership
    -0.71
    igate
    -0.71
     Imran
    -0.70
    ATIVE
    -0.70
    inen
    -0.68
     REPORT
    -0.68
    POSITIVE LOGITS
     cake
    0.94
     pudding
    0.91
    anut
    0.89
     chocolate
    0.89
     coated
    0.89
     cane
    0.84
     chip
    0.83
    âĺħâĺħ
    0.82
     flavored
    0.81
     butter
    0.81
    Activations Density 7.922%

    No Known Activations