© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    words related to political and ideological alignment

    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
    19
    +0.14
    0.7%
    98
    +0.10
    0.5%
    711
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.14
    0.00
    414
    +0.10
    0.02
    85
    +0.09
    0.02
    Negative Logits
    ¥ŀ
    -0.74
    vernment
    -0.71
     clocks
    -0.71
    ESCO
    -0.70
    undown
    -0.63
    ossibility
    -0.62
    ibility
    -0.60
    £ı
    -0.59
     coroner
    -0.59
     industrialized
    -0.58
    POSITIVE LOGITS
    pher
    0.70
     Gleaming
    0.70
    arget
    0.68
    rone
    0.65
    avering
    0.64
    arine
    0.63
    thal
    0.61
    arger
    0.61
     Disciple
    0.60
     Strongh
    0.60
    Activations Density 0.184%

    No Known Activations