© 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. 35848
    Prev
    Next
    INDEX
    Explanations

    references to medical and healthcare-related terms and 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
    +0.38
    2.3%
    459
    +0.08
    0.5%
    382
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.38
    0.39
    618
    +0.08
    0.24
    393
    +0.08
    0.36
    Negative Logits
    Copy
    -0.53
    Appearances
    -0.52
     remainder
    -0.52
    edIn
    -0.50
    itto
    -0.49
    ema
    -0.48
    anz
    -0.48
    later
    -0.48
    tsy
    -0.47
     intact
    -0.47
    POSITIVE LOGITS
     Finnish
    0.54
     Wired
    0.51
     Elliot
    0.51
     Keen
    0.51
     Ree
    0.50
     CES
    0.50
     Nikola
    0.49
     Honda
    0.49
     Freak
    0.49
     Adrian
    0.48
    Activations Density 19.336%

    No Known Activations