© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36605
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious texts and figures

    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
    430
    +0.09
    0.7%
    385
    +0.08
    0.6%
    19
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.09
    0.04
    55
    +0.08
    0.10
    466
    +0.06
    0.07
    Negative Logits
    eer
    -0.47
    eers
    -0.45
    erness
    -0.44
    Tokens
    -0.41
     Nanto
    -0.38
    Frameworks
    -0.36
     DPR
    -0.36
    yrinth
    -0.36
    tra
    -0.36
    amura
    -0.34
    POSITIVE LOGITS
    angelo
    0.51
    ctuary
    0.44
     Father
    0.42
     Almighty
    0.42
     Abraham
    0.40
    alogy
    0.39
    Father
    0.39
     Seraph
    0.39
    hood
    0.39
    ocese
    0.39
    Activations Density 8.491%

    No Known Activations