© 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. 31350
    Prev
    Next
    INDEX
    Explanations

    discussions related to government policies and political positions

    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
    +0.23
    0.9%
    23
    +0.16
    0.6%
    514
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.25
    154
    +0.16
    0.24
    514
    +0.13
    0.15
    Negative Logits
     guiActiveUnfocused
    -1.18
     adolesc
    -0.92
     Circus
    -0.90
     variance
    -0.83
    usterity
    -0.80
    çĶ°
    -0.78
     Barrier
    -0.75
     Obst
    -0.75
     discrep
    -0.74
     fertility
    -0.73
    POSITIVE LOGITS
    ates
    1.18
    should
    1.11
    alone
    1.05
    said
    1.03
    ¯
    1.03
    could
    1.02
    dl
    1.00
    thy
    0.99
    ked
    0.99
    might
    0.98
    Activations Density 9.005%

    No Known Activations