© 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 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. 33294
    Prev
    Next
    INDEX
    Explanations

    topics related to wireless technology and internet connectivity

    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
    288
    +0.19
    0.9%
    447
    +0.16
    0.8%
    578
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.20
    99
    +0.16
    0.10
    326
    +0.13
    0.17
    Negative Logits
    ablishment
    -0.83
    itia
    -0.81
    udo
    -0.79
     Rite
    -0.79
    ivia
    -0.79
    oldemort
    -0.76
     Minerva
    -0.75
     Unch
    -0.75
    emis
    -0.74
    yrinth
    -0.73
    POSITIVE LOGITS
    phone
    0.88
     carriers
    0.82
     broadband
    0.79
     communication
    0.77
    erness
    0.77
     headsets
    0.75
     communications
    0.73
     carrier
    0.73
     imaging
    0.72
     networking
    0.71
    Activations Density 5.563%

    No Known Activations