© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    references to historical events, government actions, and political controversies

    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
    160
    +0.19
    0.7%
    746
    +0.17
    0.6%
    641
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.19
    0.04
    627
    +0.17
    0.05
    641
    +0.17
    0.05
    Negative Logits
     Fletcher
    -1.04
     Dragonbound
    -0.99
     Syl
    -0.98
    ãĤ©
    -0.97
    etheless
    -0.96
    ļéĨĴ
    -0.95
    ogy
    -0.95
     ko
    -0.94
     gorilla
    -0.93
     Budd
    -0.93
    POSITIVE LOGITS
    11
    1.44
    2012
    1.40
    2013
    1.40
    2014
    1.38
    2015
    1.36
    12
    1.36
    1000
    1.35
    2011
    1.31
    2017
    1.30
    oct
    1.30
    Activations Density 0.752%

    No Known Activations