© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1480
    Prev
    Next
    INDEX
    Explanations

    phrases related to lobbying and government influence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.21
    0.9%
    679
    +0.20
    0.8%
    526
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.08
    346
    +0.20
    0.04
    679
    +0.17
    0.06
    Negative Logits
    fal
    -0.97
     Apostles
    -0.83
    hang
    -0.81
     Carbuncle
    -0.80
    hani
    -0.77
    cond
    -0.74
    âĵĺ
    -0.74
    esm
    -0.73
    bridge
    -0.73
    bian
    -0.73
    POSITIVE LOGITS
    uppet
    0.93
     lobbying
    0.91
     furiously
    0.89
     lobb
    0.87
    uese
    0.86
    busters
    0.82
    atures
    0.80
     droid
    0.79
    erson
    0.78
     pedd
    0.78
    Activations Density 0.777%

    No Known Activations