© 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. 39704
    Prev
    Next
    INDEX
    Explanations

    phrases discussing actions or concepts happening outside a specific context or realm

    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
    +0.11
    0.5%
    693
    +0.10
    0.5%
    662
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.11
    0.08
    109
    +0.10
    0.07
    710
    +0.10
    0.08
    Negative Logits
    enegger
    -0.78
    anche
    -0.78
    onder
    -0.76
    chief
    -0.73
    vous
    -0.73
    antine
    -0.72
    cca
    -0.72
    ulously
    -0.71
    killer
    -0.70
    ulous
    -0.70
    POSITIVE LOGITS
     observer
    0.80
    etheless
    0.76
     observers
    0.76
     Borders
    0.73
    shock
    0.73
     academia
    0.71
    outside
    0.69
     spitting
    0.64
     peripher
    0.64
     parties
    0.64
    Activations Density 5.339%

    No Known Activations