© 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. 46047
    Prev
    Next
    INDEX
    Explanations

    politically related words and names, possibly related to parliamentary discussions or government officials

    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
    502
    +0.03
    0.5%
    447
    +0.03
    0.4%
    355
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.03
    0.17
    547
    +0.03
    0.10
    556
    +0.03
    0.12
    Negative Logits
    icides
    -0.21
    ulia
    -0.20
    ansas
    -0.20
    favorite
    -0.19
    Miami
    -0.18
    Colorado
    -0.18
    mys
    -0.18
    âĸ¬
    -0.17
    population
    -0.17
     ordinances
    -0.17
    POSITIVE LOGITS
     Cheong
    0.26
    agher
    0.25
    zinski
    0.24
     QC
    0.23
    è¦ļéĨĴ
    0.23
     warned
    0.23
     labelled
    0.23
     hinted
    0.22
     briefed
    0.22
     reiterated
    0.22
    Activations Density 8.184%

    No Known Activations