© 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. 40862
    Prev
    Next
    INDEX
    Explanations

    dates and specific days of the week

    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
    +0.21
    0.9%
    430
    +0.12
    0.5%
    89
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.10
    663
    +0.12
    0.07
    536
    +0.11
    0.07
    Negative Logits
    mbuds
    -0.74
     persecuted
    -0.63
    illas
    -0.63
     predec
    -0.62
     synonymous
    -0.60
     showc
    -0.60
    ufact
    -0.59
    cies
    -0.59
    Marginal
    -0.59
     tame
    -0.58
    POSITIVE LOGITS
    ioxide
    0.95
    ulhu
    0.94
     onwards
    0.89
     Anniversary
    0.85
    endment
    0.85
     anniversary
    0.83
     2018
    0.83
     Amendment
    0.82
    ruary
    0.81
     birthday
    0.81
    Activations Density 6.116%

    No Known Activations