© 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
    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. 14299
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics or conflicts

    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
    640
    +0.17
    0.8%
    447
    +0.15
    0.7%
    152
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.20
    152
    +0.15
    0.17
    124
    +0.12
    0.15
    Negative Logits
    ulhu
    -0.84
     Doomsday
    -0.76
    Ń·
    -0.75
    kson
    -0.74
     Phi
    -0.71
    ħĭ
    -0.68
    ļéĨĴ
    -0.67
    姫
    -0.65
    £ı
    -0.65
     Wiz
    -0.64
    POSITIVE LOGITS
    bred
    1.10
    touch
    1.07
    class
    1.06
    sized
    1.03
    performing
    1.02
    educated
    1.01
    produced
    0.98
    end
    0.97
    run
    0.96
    rate
    0.96
    Activations Density 6.169%

    No Known Activations