© 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. 31499
    Prev
    Next
    INDEX
    Explanations

    references to personal possessions and characteristics, and discussions about personal beliefs and opinions

    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
    +0.20
    0.9%
    393
    +0.19
    0.8%
    481
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.22
    608
    +0.19
    0.16
    362
    +0.17
    0.12
    Negative Logits
    ij士
    -0.93
    obin
    -0.85
    arians
    -0.83
    Alert
    -0.81
    olkien
    -0.80
    lehem
    -0.79
    ĪĴ
    -0.79
     Reduce
    -0.79
    udo
    -0.78
    lein
    -0.75
    POSITIVE LOGITS
     own
    1.34
     favourite
    1.09
     eyes
    1.09
     favorite
    1.08
     footsteps
    1.05
     gaze
    1.05
     belongings
    1.03
     throats
    0.99
     knees
    0.99
     genitals
    0.98
    Activations Density 8.326%

    No Known Activations