© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    phrases related to joining or joining forces

    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
    •Layer 6 UMAP region: Mixed in middle - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.25
    0.8%
    526
    +0.20
    0.6%
    746
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.25
    0.04
    101
    +0.20
    0.04
    176
    +0.17
    0.03
    Negative Logits
    rag
    -1.13
     tiss
    -1.08
    bane
    -1.02
    genic
    -0.95
     tuber
    -0.94
    binary
    -0.91
    mercial
    -0.90
    intendent
    -0.90
    agic
    -0.88
    ogene
    -0.87
    POSITIVE LOGITS
     chats
    1.01
    ãĥĥ
    0.99
    lehem
    0.98
     forces
    0.97
     ranks
    0.94
    lift
    0.94
    eries
    0.94
     Kens
    0.94
     join
    0.93
    fleet
    0.93
    Activations Density 0.432%

    No Known Activations