© 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 EvalsExportsAPI 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. 33666
    Prev
    Next
    INDEX
    Explanations

    terms related to military conscription or recruitment

    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
    339
    +0.16
    0.6%
    447
    +0.13
    0.5%
    370
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.16
    0.09
    18
    +0.13
    0.08
    721
    +0.13
    0.06
    Negative Logits
     oats
    -0.91
    lihood
    -0.90
     Hour
    -0.88
     Peaks
    -0.87
    baugh
    -0.86
     streams
    -0.85
    WOOD
    -0.83
    jiang
    -0.81
    neath
    -0.81
     Shoals
    -0.81
    POSITIVE LOGITS
    cientious
    1.46
    cription
    1.44
    cript
    1.43
    oled
    1.32
    pired
    1.29
    ensual
    1.29
    idered
    1.27
    oci
    1.23
    igned
    1.23
    cient
    1.22
    Activations Density 5.896%

    No Known Activations