© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35497
    Prev
    Next
    INDEX
    Explanations

    phrases posing questions or considerations with the word "should"

    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
    +0.14
    0.6%
    285
    +0.12
    0.5%
    326
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.14
    0.13
    23
    +0.12
    0.11
    285
    +0.12
    0.07
    Negative Logits
    stood
    -0.74
     sclerosis
    -0.73
     Finder
    -0.69
    atile
    -0.69
     Fra
    -0.69
    cule
    -0.67
     Puzzle
    -0.66
     Vers
    -0.64
     Pon
    -0.61
     ROS
    -0.61
    POSITIVE LOGITS
    ered
    1.09
    ering
    1.02
    uel
    0.89
    n
    0.87
    icum
    0.86
    ublic
    0.85
    arget
    0.84
     be
    0.83
    ember
    0.83
    erest
    0.82
    Activations Density 6.805%

    No Known Activations