© 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. 4754
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and sequence

    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%
    455
    +0.11
    0.5%
    746
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.23
    546
    +0.11
    0.09
    554
    +0.10
    -0.09
    Negative Logits
    Ble
    -0.72
    ignment
    -0.72
    mad
    -0.71
    hab
    -0.65
    ampa
    -0.65
     Might
    -0.62
    emen
    -0.62
    eting
    -0.61
     Pole
    -0.61
     Wish
    -0.61
    POSITIVE LOGITS
     regretted
    0.85
     deleted
    0.79
     reinstated
    0.79
     confir
    0.78
     recons
    0.78
     discovered
    0.78
    shown
    0.77
     succumbed
    0.77
     clarified
    0.77
     reapp
    0.76
    Activations Density 8.676%

    No Known Activations