© 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. 31970
    Prev
    Next
    INDEX
    Explanations

    references and discussions related to medical trials, placebos, and treatment effects, especially in the context of drug studies

    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
    420
    +0.13
    0.8%
    444
    +0.12
    0.7%
    447
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.13
    0.08
    124
    +0.12
    0.12
    5
    +0.11
    0.04
    Negative Logits
    omy
    -0.68
     IPM
    -0.67
    ticket
    -0.65
    hani
    -0.60
    oras
    -0.59
    riad
    -0.58
     creditors
    -0.56
    arya
    -0.56
    DON
    -0.56
    lar
    -0.55
    POSITIVE LOGITS
     halves
    0.61
     Columb
    0.57
     Springs
    0.56
     placebo
    0.55
     analges
    0.54
    lette
    0.54
    warm
    0.53
    aneous
    0.53
     padded
    0.52
    ysc
    0.52
    Activations Density 9.333%

    No Known Activations