© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35295
    Prev
    Next
    INDEX
    Explanations

    phrases related to cruise ships and naval activities

    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
    +0.10
    0.7%
    607
    +0.09
    0.6%
    288
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.10
    0.03
    374
    +0.09
    0.05
    547
    +0.09
    0.03
    Negative Logits
    older
    -0.54
    BLIC
    -0.50
    iotic
    -0.49
    sembly
    -0.49
    lder
    -0.49
    ĪĴ
    -0.48
    ths
    -0.48
    SourceFile
    -0.48
    sie
    -0.47
    lr
    -0.47
    POSITIVE LOGITS
     cruise
    0.71
     Cruise
    0.66
     Missile
    0.57
     missile
    0.57
     liner
    0.56
     missiles
    0.55
     ferry
    0.51
     cruising
    0.50
     ship
    0.50
     sailing
    0.49
    Activations Density 9.551%

    No Known Activations