© 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. 32425
    Prev
    Next
    INDEX
    Explanations

    references to and discussions about military and security-related topics

    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
    288
    +0.23
    1.0%
    447
    +0.18
    0.8%
    635
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    635
    +0.23
    0.07
    695
    +0.18
    0.06
    618
    +0.14
    0.10
    Negative Logits
    20439
    -0.94
    âĶģ
    -0.93
    heimer
    -0.86
    gger
    -0.84
    terness
    -0.83
    apest
    -0.82
    nob
    -0.82
    ividual
    -0.82
    galitarian
    -0.81
    lies
    -0.80
    POSITIVE LOGITS
     fatig
    1.13
     dictatorship
    1.04
     commanders
    1.03
     acad
    1.03
     personnel
    1.02
     contractor
    1.00
     academy
    0.96
     readiness
    0.95
     intervention
    0.95
     contractors
    0.93
    Activations Density 9.802%

    No Known Activations