© 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. 32882
    Prev
    Next
    INDEX
    Explanations

    numbers, including values and quantities

    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
    0.8%
    501
    +0.13
    0.6%
    493
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.16
    0.05
    49
    +0.13
    0.12
    739
    +0.11
    0.02
    Negative Logits
    rina
    -0.66
    afety
    -0.64
    itiz
    -0.64
    uria
    -0.57
     Machina
    -0.57
    esis
    -0.56
     institution
    -0.54
    growth
    -0.54
    stem
    -0.53
     backlog
    -0.52
    POSITIVE LOGITS
     respectively
    1.88
     alike
    1.44
     together
    1.00
     jointly
    0.95
    together
    0.94
     respective
    0.91
    depending
    0.84
     collide
    0.82
    OTH
    0.77
     separately
    0.72
    Activations Density 20.058%

    No Known Activations