© 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. 35022
    Prev
    Next
    INDEX
    Explanations

    computer code syntax and technical instructions

    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
    553
    +0.12
    0.5%
    496
    +0.12
    0.5%
    323
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.12
    0.07
    323
    +0.12
    0.09
    598
    +0.11
    0.04
    Negative Logits
    Bron
    -0.81
     Scientist
    -0.77
    zan
    -0.76
    negie
    -0.72
    anto
    -0.70
    utic
    -0.70
    pees
    -0.69
     PET
    -0.69
     Science
    -0.68
    olis
    -0.68
    POSITIVE LOGITS
    ãģ®æ
    0.83
    ãģ®éŃĶ
    0.75
     wardrobe
    0.74
     remake
    0.69
    ()
    0.68
     TAMADRA
    0.68
    çİĭ
    0.68
     float
    0.67
    }}}
    0.66
    ¾
    0.66
    Activations Density 8.466%

    No Known Activations