© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35776
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications companies, regulations, and issues such as net neutrality and government surveillance

    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
    213
    +0.07
    0.6%
    484
    +0.06
    0.6%
    447
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.19
    146
    +0.06
    0.09
    213
    +0.05
    0.05
    Negative Logits
    ilts
    -0.41
     Boyle
    -0.39
    lain
    -0.37
     Klingon
    -0.36
     Ryder
    -0.36
    auder
    -0.35
     Spock
    -0.35
    iewicz
    -0.34
    udo
    -0.34
     Kenobi
    -0.33
    POSITIVE LOGITS
     Regulatory
    0.41
    sav
    0.39
    STON
    0.38
     corrid
    0.36
    levision
    0.36
    s
    0.36
    æ©Ł
    0.34
    CAST
    0.34
    LECT
    0.33
     sector
    0.33
    Activations Density 5.263%

    No Known Activations