© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6023
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people's names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    556
    +0.14
    0.5%
    520
    +0.13
    0.5%
    574
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.14
    0.06
    284
    +0.13
    0.05
    659
    +0.12
    0.05
    Negative Logits
    ModLoader
    -1.06
     Siren
    -0.92
     uter
    -0.91
    thumbnails
    -0.90
    20439
    -0.89
     womb
    -0.85
    mercial
    -0.85
    Detroit
    -0.85
     uterus
    -0.83
    ecause
    -0.83
    POSITIVE LOGITS
    furt
    1.05
    ¹
    1.04
    lund
    1.04
    ª
    0.91
    fur
    0.90
     McKay
    0.87
    isher
    0.86
    ĩ
    0.86
     Kramer
    0.86
    rack
    0.86
    Activations Density 0.476%

    No Known Activations