© 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. 13123
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms and medical terminology

    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
    377
    +0.05
    0.7%
    566
    +0.05
    0.6%
    146
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.05
    0.24
    352
    +0.05
    0.19
    154
    +0.04
    0.20
    Negative Logits
    ozo
    -0.31
     Boone
    -0.28
     Blackwell
    -0.26
    iated
    -0.26
    oses
    -0.25
    inventoryQuantity
    -0.24
    ified
    -0.21
    oner
    -0.21
    iano
    -0.21
     Lite
    -0.21
    POSITIVE LOGITS
    selage
    0.34
    ornia
    0.34
    RIC
    0.30
    chieve
    0.29
    htaking
    0.27
    sterdam
    0.27
    camp
    0.26
    SPA
    0.26
    ghan
    0.26
    URA
    0.26
    Activations Density 11.970%

    No Known Activations