© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40748
    Prev
    Next
    INDEX
    Explanations

    archaic English pronouns and possessive pronouns

    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
    14
    +0.16
    0.7%
    326
    +0.14
    0.6%
    316
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.16
    0.16
    326
    +0.14
    0.19
    571
    +0.14
    0.10
    Negative Logits
     Hayward
    -0.84
    eteria
    -0.81
     Rapp
    -0.80
    ersion
    -0.80
    iott
    -0.79
    endo
    -0.77
    ãĥ¼ãĤ¯
    -0.76
    isson
    -0.76
     Cheong
    -0.75
    acca
    -0.75
    POSITIVE LOGITS
     shalt
    1.42
     thou
    1.06
    selves
    1.03
    self
    1.00
     Thou
    0.99
     hast
    0.97
     thy
    0.93
     wast
    0.84
     scalp
    0.82
     livest
    0.81
    Activations Density 5.952%

    No Known Activations