© 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. 46007
    Prev
    Next
    INDEX
    Explanations

    sentences containing temporal frequencies, such as "every single day" or "every 4.5 hours"

    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
    +0.13
    1.1%
    686
    +0.05
    0.4%
    571
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.13
    0.10
    289
    +0.05
    -0.03
    614
    +0.05
    0.04
    Negative Logits
     Journals
    -0.37
    ahime
    -0.36
     Esports
    -0.32
    igans
    -0.31
    ELL
    -0.30
     ESP
    -0.30
    rigan
    -0.30
    hess
    -0.30
     Jacobs
    -0.29
    advertising
    -0.29
    POSITIVE LOGITS
     year
    0.49
     month
    0.48
    where
    0.47
    ħĭ
    0.46
    Ĥª
    0.44
     week
    0.44
    morning
    0.42
    things
    0.42
    single
    0.41
     day
    0.41
    Activations Density 10.123%

    No Known Activations