© 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. 39622
    Prev
    Next
    INDEX
    Explanations

    news-related phrases and information

    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
    +0.24
    1.0%
    430
    +0.12
    0.5%
    501
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.24
    0.08
    430
    +0.12
    0.15
    279
    +0.10
    0.09
    Negative Logits
    aughed
    -0.78
     Conquer
    -0.74
     Viz
    -0.73
    emaker
    -0.72
    sed
    -0.72
    ordes
    -0.68
    chief
    -0.68
    negie
    -0.66
    vet
    -0.65
     Trouble
    -0.65
    POSITIVE LOGITS
     afternoon
    1.35
     morning
    1.30
     evening
    1.19
     mornings
    1.01
    morning
    0.87
     night
    0.83
    days
    0.79
     Tonight
    0.77
     NIGHT
    0.76
     Evening
    0.76
    Activations Density 8.436%

    No Known Activations