© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    references to military operations and weaponry, specifically focusing on missiles

    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
    288
    +0.30
    1.1%
    101
    +0.15
    0.5%
    137
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.30
    0.08
    326
    +0.15
    0.05
    325
    +0.13
    0.04
    Negative Logits
    gres
    -1.29
    redo
    -1.11
    ORD
    -0.99
    Vert
    -0.98
    orld
    -0.98
    ä
    -0.97
    âĸ¬âĸ¬
    -0.96
    çĶ°
    -0.94
    ---------
    -0.93
    lv
    -0.93
    POSITIVE LOGITS
     launcher
    1.43
     launchers
    1.40
     barr
    1.33
     missiles
    1.28
     warheads
    1.26
    oons
    1.25
     missile
    1.22
     propelled
    1.22
     Launcher
    1.19
     submarines
    1.14
    Activations Density 0.710%

    No Known Activations