© 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 Local
    9. 6-RES_SCL-AJT
    11. 35720
    Prev
    Next
    INDEX
    Explanations

    phrases related to military deployments and operations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.33
    1.7%
    551
    +0.13
    0.6%
    665
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.33
    0.27
    149
    +0.13
    0.09
    551
    +0.12
    0.13
    Negative Logits
    Lear
    -0.57
    amped
    -0.57
    reality
    -0.56
     misunderstanding
    -0.56
    76561
    -0.55
    establishment
    -0.55
     abstraction
    -0.55
    Mom
    -0.55
    processing
    -0.54
    existence
    -0.53
    POSITIVE LOGITS
     be
    1.08
     undoubtedly
    1.04
     doubtless
    1.02
     continue
    0.98
     likely
    0.97
     probably
    0.92
     surely
    0.91
     hopefully
    0.89
     gladly
    0.89
     definitely
    0.88
    Activations Density 14.430%

    No Known Activations