© 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. 14258
    Prev
    Next
    INDEX
    Explanations

    dates and times in a specific format

    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
    +0.17
    0.8%
    430
    +0.13
    0.6%
    726
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.17
    0.13
    384
    +0.13
    0.05
    240
    +0.11
    0.06
    Negative Logits
    ership
    -0.94
    hip
    -0.85
    atche
    -0.82
    itton
    -0.79
    ris
    -0.77
    abet
    -0.76
    aeda
    -0.75
    ports
    -0.75
    vironment
    -0.73
    naire
    -0.72
    POSITIVE LOGITS
     morning
    1.36
     afternoon
    1.36
     night
    1.22
     evening
    1.17
     mornings
    1.16
     Night
    1.10
     nights
    1.03
     evenings
    0.92
    Night
    0.90
     twilight
    0.86
    Activations Density 3.012%

    No Known Activations