© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    political and social topics, particularly focusing on controversies and government actions

    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
    447
    +0.22
    1.0%
    102
    +0.11
    0.5%
    517
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.22
    0.20
    154
    +0.11
    0.19
    23
    +0.10
    0.18
    Negative Logits
     Ruk
    -0.78
     Aman
    -0.70
     Bris
    -0.68
     Stard
    -0.68
     Kitt
    -0.67
     Jeanne
    -0.67
     Qiao
    -0.67
     Maurit
    -0.66
     Belg
    -0.65
     Sieg
    -0.64
    POSITIVE LOGITS
    ª
    0.91
    possibly
    0.91
    very
    0.88
    yet
    0.86
    urion
    0.85
    ordinary
    0.84
    Ĵ
    0.83
    ittal
    0.83
    virtual
    0.83
    ¹
    0.82
    Activations Density 4.160%

    No Known Activations