© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35067
    Prev
    Next
    INDEX
    Explanations

    physical measurements and related terms, especially in the context of scientific experiments and medical procedures

    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
    1.1%
    255
    +0.12
    0.6%
    497
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.14
    557
    +0.12
    0.09
    89
    +0.09
    0.07
    Negative Logits
    illard
    -0.78
    udeb
    -0.66
    chrome
    -0.64
    ccoli
    -0.61
    ategor
    -0.60
    osi
    -0.58
     Safari
    -0.57
    ovie
    -0.56
    burning
    -0.56
    paragraph
    -0.56
    POSITIVE LOGITS
     Measure
    0.81
    Measure
    0.80
     measurement
    0.80
     measurements
    0.79
     measuring
    0.74
     instruments
    0.70
     metrics
    0.69
    asured
    0.69
     measure
    0.65
    asure
    0.64
    Activations Density 9.012%

    No Known Activations