© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    discussion related to various political and societal topics, including health insurance, legal protections, and public financing

    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
    314
    +0.18
    0.7%
    640
    +0.15
    0.6%
    152
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.18
    0.15
    124
    +0.15
    0.13
    537
    +0.14
    0.13
    Negative Logits
     Dickinson
    -0.98
     Burr
    -0.95
     Ital
    -0.88
     Borders
    -0.85
     Shaw
    -0.84
     Holt
    -0.80
     Norris
    -0.79
     Hanna
    -0.79
     Burnett
    -0.78
     Christensen
    -0.78
    POSITIVE LOGITS
    related
    1.47
    based
    1.45
    centric
    1.41
    style
    1.41
    specific
    1.40
    level
    1.39
    themed
    1.38
    derived
    1.38
    type
    1.38
    training
    1.37
    Activations Density 0.964%

    No Known Activations