© 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. 5059
    Prev
    Next
    INDEX
    Explanations

    medical terms related to conditions and treatments

    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
    203
    +0.10
    0.6%
    483
    +0.09
    0.5%
    453
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.10
    738
    +0.09
    0.06
    406
    +0.07
    0.09
    Negative Logits
    forth
    -0.77
    ativity
    -0.60
     Forth
    -0.58
     Guth
    -0.57
     Watkins
    -0.56
     Louie
    -0.56
     Mah
    -0.53
     Creed
    -0.53
     Rooney
    -0.51
     Shank
    -0.51
    POSITIVE LOGITS
    и
    0.64
    scl
    0.62
    idem
    0.61
    ect
    0.60
    idine
    0.58
    Ĥİ
    0.55
    material
    0.54
    dust
    0.54
    EStream
    0.54
    ynthesis
    0.53
    Activations Density 8.684%

    No Known Activations