© 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. 34003
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial issues or topics

    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
    +0.20
    1.1%
    481
    +0.10
    0.5%
    146
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.20
    0.30
    138
    +0.10
    0.28
    64
    +0.09
    -0.18
    Negative Logits
     SPR
    -0.51
     Mamm
    -0.51
     Suzuki
    -0.48
    mount
    -0.47
     Boone
    -0.47
     Lunar
    -0.46
    vik
    -0.46
     Dinosaur
    -0.46
    Motor
    -0.46
    Spl
    -0.45
    POSITIVE LOGITS
     pursuant
    0.64
     namely
    0.60
    iatus
    0.59
     altogether
    0.57
     abroad
    0.57
     disag
    0.55
    anship
    0.55
     because
    0.55
     whatsoever
    0.54
     globally
    0.54
    Activations Density 8.126%

    No Known Activations