© 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. 35790
    Prev
    Next
    INDEX
    Explanations

    phrases related to mechanical components and equipment

    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
    376
    +0.07
    0.5%
    174
    +0.07
    0.5%
    132
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.24
    613
    +0.07
    0.09
    316
    +0.07
    0.08
    Negative Logits
    ICLE
    -0.45
    ACA
    -0.37
     glim
    -0.37
     Spaces
    -0.36
     pige
    -0.36
    alia
    -0.36
     retrospective
    -0.36
    raviolet
    -0.36
     quarters
    -0.35
    IVE
    -0.34
    POSITIVE LOGITS
    olean
    0.59
    edia
    0.55
    eus
    0.54
    ertodd
    0.54
    ogle
    0.53
    obil
    0.50
    xon
    0.50
    ãĤ£
    0.48
    ption
    0.47
     Polo
    0.47
    Activations Density 9.559%

    No Known Activations