© 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. 36399
    Prev
    Next
    INDEX
    Explanations

    terms related to network latency and lags

    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
    757
    +0.11
    0.6%
    232
    +0.10
    0.5%
    240
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.21
    326
    +0.10
    0.20
    195
    +0.10
    -0.01
    Negative Logits
    IBLE
    -0.75
    theless
    -0.72
    terday
    -0.70
    ortium
    -0.65
     Dangerous
    -0.62
     captcha
    -0.60
     toget
    -0.58
    ãĥ¯ãĥ³
    -0.57
    taining
    -0.57
    ×ij
    -0.57
    POSITIVE LOGITS
    oon
    1.09
    uten
    0.82
    arde
    0.80
    omorph
    0.80
    lag
    0.77
    una
    0.76
    gers
    0.75
    ering
    0.74
     lag
    0.74
    rang
    0.74
    Activations Density 7.031%

    No Known Activations