© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11508
    Prev
    Next
    INDEX
    Explanations

    technical terms related to geology or mineralogy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    213
    +0.15
    0.6%
    566
    +0.15
    0.6%
    707
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.05
    289
    +0.15
    0.02
    659
    +0.15
    0.04
    Negative Logits
    izable
    -1.01
    ilater
    -0.96
    mort
    -0.90
    ding
    -0.89
     Sands
    -0.87
    fell
    -0.85
    ified
    -0.84
     coloured
    -0.84
    ned
    -0.83
    ished
    -0.82
    POSITIVE LOGITS
    ĥ
    1.39
    Ĵ
    1.38
    ķ
    1.35
    Į
    1.27
    Ģ
    1.27
    ı
    1.24
    Ķ
    1.23
    Ľ
    1.21
    IJ
    1.21
    Ĺ
    1.20
    Activations Density 0.800%

    No Known Activations