© 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. 36072
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming and software development

    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
    503
    +0.11
    0.6%
    685
    +0.10
    0.6%
    549
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.08
    619
    +0.10
    0.08
    688
    +0.10
    0.06
    Negative Logits
    mind
    -0.58
     volume
    -0.55
     maize
    -0.54
     Cinnamon
    -0.54
     Maw
    -0.53
     living
    -0.53
    glers
    -0.52
     Zeit
    -0.51
     lungs
    -0.51
     Farn
    -0.50
    POSITIVE LOGITS
    etric
    1.21
    ilitary
    1.19
    agnetic
    1.06
    etr
    1.06
    eter
    1.04
    ilit
    1.03
    etrical
    1.00
    olic
    0.92
    eters
    0.89
    otor
    0.87
    Activations Density 7.462%

    No Known Activations