Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5428
    Prev
    Next
    INDEX
    Explanations

    mentions of military exercises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    5
    +0.08
    0.5%
    461
    +0.08
    0.5%
    618
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.08
    0.01
    644
    +0.08
    0.01
    460
    +0.08
    0.01
    Negative Logits
     Hep
    -0.60
     ignition
    -0.58
     deed
    -0.54
    443
    -0.51
     balance
    -0.50
     door
    -0.50
     Ign
    -0.49
     sip
    -0.49
     dust
    -0.48
     Covenant
    -0.47
    POSITIVE LOGITS
    bourg
    0.71
    andise
    0.66
    eries
    0.63
    soDeliveryDate
    0.62
    ailand
    0.60
    intendent
    0.57
     Prix
    0.57
    illac
    0.57
     exercises
    0.57
    rand
    0.57
    Activations Density 0.006%

    No Known Activations