© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    words related to legal and medical terminology, with a focus on specific medical conditions and legal terms

    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
    381
    +0.14
    0.6%
    726
    +0.13
    0.5%
    600
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.14
    0.10
    651
    +0.13
    0.08
    259
    +0.12
    0.05
    Negative Logits
     parting
    -1.00
    NetMessage
    -0.92
     prevail
    -0.81
     destro
    -0.80
     resil
    -0.80
     prevailing
    -0.79
     Torn
    -0.78
     refuel
    -0.75
     warr
    -0.74
     herbs
    -0.74
    POSITIVE LOGITS
    ocracy
    1.26
    utions
    1.16
    onal
    1.14
    arius
    1.10
    amins
    1.09
    ople
    1.08
    atis
    1.08
    rification
    1.07
    aires
    1.06
    ocratic
    1.06
    Activations Density 4.626%

    No Known Activations