© 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. 3756
    Prev
    Next
    INDEX
    Explanations

    mentions of royalty and noble titles

    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
    414
    +0.04
    0.4%
    479
    +0.04
    0.4%
    102
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.04
    0.05
    24
    +0.04
    0.07
    603
    +0.03
    0.08
    Negative Logits
    okin
    -0.30
    ppo
    -0.29
    uters
    -0.29
    osion
    -0.28
    tools
    -0.27
    OPA
    -0.27
    oÄŁ
    -0.26
     outage
    -0.26
    Pak
    -0.26
    pson
    -0.26
    POSITIVE LOGITS
     Mary
    0.38
     Elizabeth
    0.38
     Duchess
    0.34
     Emma
    0.33
    hips
    0.33
    esses
    0.32
     Leia
    0.32
     Jacqu
    0.32
     Catherine
    0.32
     Alexandra
    0.31
    Activations Density 7.114%

    No Known Activations