© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 982
    Prev
    Next
    INDEX
    Explanations

    mentions of soybeans and their related topics

    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
    392
    +0.04
    0.5%
    203
    +0.04
    0.5%
    23
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.04
    0.07
    326
    +0.04
    0.05
    343
    +0.04
    0.04
    Negative Logits
    UCT
    -0.32
     Humanity
    -0.28
    ESS
    -0.27
    hani
    -0.27
    IGN
    -0.26
    IME
    -0.26
     CBI
    -0.25
    theless
    -0.25
     Cipher
    -0.25
    UTERS
    -0.24
    POSITIVE LOGITS
    beans
    0.62
    bean
    0.61
    opot
    0.34
    atown
    0.33
    bowl
    0.33
    war
    0.33
    ju
    0.33
    uana
    0.33
    ovy
    0.32
    lda
    0.32
    Activations Density 0.479%

    No Known Activations