© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4103
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social systems, particularly issues of corruption, bias, structural inequalities, and the functioning of the legal and political system

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.27
    1.5%
    288
    +0.13
    0.7%
    527
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.22
    328
    +0.13
    0.07
    703
    +0.10
    0.08
    Negative Logits
    tein
    -0.63
    ãĤ¤ãĥĪ
    -0.60
    urous
    -0.58
     earnest
    -0.58
    ishable
    -0.57
    ãĥģ
    -0.57
    spell
    -0.56
    noon
    -0.56
    EMP
    -0.55
    æĢ
    -0.54
    POSITIVE LOGITS
    atics
    0.93
    atically
    0.74
    wide
    0.72
    ologies
    0.72
    ically
    0.70
    atic
    0.63
    atism
    0.61
    etting
    0.59
     integ
    0.59
    entric
    0.58
    Activations Density 10.050%

    No Known Activations