© 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. 33874
    Prev
    Next
    INDEX
    Explanations

    proper names or nouns, specifically focusing on the name "Ian"

    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
    +0.20
    1.0%
    201
    +0.10
    0.5%
    559
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.20
    0.08
    659
    +0.10
    0.10
    656
    +0.10
    0.08
    Negative Logits
    ktop
    -0.96
    adobe
    -0.77
    âĶģ
    -0.74
    perm
    -0.70
    escal
    -0.70
    liga
    -0.68
    DAQ
    -0.67
    hips
    -0.66
    Moscow
    -0.66
    KI
    -0.65
    POSITIVE LOGITS
     Cheong
    0.92
     Ian
    0.85
     Fleming
    0.78
     Wright
    0.77
    odox
    0.76
     Thomson
    0.75
     Curtis
    0.74
     Neal
    0.72
     Som
    0.72
     Dice
    0.72
    Activations Density 5.628%

    No Known Activations