© 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. 32136
    Prev
    Next
    INDEX
    Explanations

    proper names with unusual characters or symbols

    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
    +0.16
    0.6%
    314
    +0.14
    0.6%
    675
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.23
    447
    +0.14
    0.24
    675
    +0.12
    0.19
    Negative Logits
     obser
    -0.89
     warr
    -0.88
     condem
    -0.85
     unwanted
    -0.84
     ponder
    -0.83
     contrace
    -0.82
     imagination
    -0.82
     sacrific
    -0.82
     advoc
    -0.80
     disadvant
    -0.80
    POSITIVE LOGITS
    ï¸ı
    1.24
    ¯
    1.13
    xxx
    1.09
    tra
    1.07
    âĻ¦
    1.06
    °
    1.04
    âĻ
    1.00
    tab
    0.99
    rh
    0.99
    hole
    0.99
    Activations Density 12.380%

    No Known Activations