© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    various contexts where the word "exhausted" is prominently featured

    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
    +0.12
    1.5%
    351
    +0.04
    0.6%
    277
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.12
    0.06
    255
    +0.04
    0.11
    1
    +0.04
    0.11
    Negative Logits
    atory
    -0.28
    ties
    -0.27
    abet
    -0.27
    ood
    -0.26
     tune
    -0.26
    hips
    -0.25
    breeding
    -0.24
    friend
    -0.24
    ificantly
    -0.24
    rim
    -0.24
    POSITIVE LOGITS
     overwhelmed
    0.28
     Tess
    0.27
     exhausted
    0.27
    cules
    0.26
    ADRA
    0.26
    uron
    0.25
    mble
    0.24
     unbeliev
    0.24
     Dunn
    0.23
    vier
    0.23
    Activations Density 18.563%

    No Known Activations