© 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. 40743
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns referring to specific individuals and interpersonal interactions

    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
    481
    +0.18
    0.7%
    420
    +0.13
    0.5%
    598
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.32
    566
    +0.13
    0.17
    354
    +0.12
    0.16
    Negative Logits
     Canaver
    -0.81
     Checking
    -0.76
    fing
    -0.75
    noticed
    -0.75
    grid
    -0.75
     Nanto
    -0.74
     Whale
    -0.71
    Fla
    -0.71
    JD
    -0.70
    Loading
    -0.70
    POSITIVE LOGITS
     ruins
    0.85
    Äĩ
    0.84
    're
    0.80
     bureaucr
    0.78
     deserved
    0.78
     expire
    0.76
    ubi
    0.76
     deterior
    0.76
     disappears
    0.76
     cooper
    0.75
    Activations Density 12.432%

    No Known Activations