© 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. 40848
    Prev
    Next
    INDEX
    Explanations

    references to biblical figures and prophecies

    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
    132
    +0.12
    0.6%
    447
    +0.10
    0.6%
    572
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.12
    0.08
    577
    +0.10
    0.10
    48
    +0.10
    0.10
    Negative Logits
     Parenthood
    -0.74
    emonium
    -0.73
    estone
    -0.71
    iments
    -0.67
     Popular
    -0.64
     pestic
    -0.64
    ername
    -0.64
    essee
    -0.62
    iment
    -0.61
    igo
    -0.60
    POSITIVE LOGITS
    iah
    0.72
    hawks
    0.70
    awk
    0.69
    hovah
    0.64
    phal
    0.64
    tml
    0.61
    awks
    0.60
     Authority
    0.60
    ttp
    0.59
     Carey
    0.58
    Activations Density 17.510%

    No Known Activations