© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 266
    Prev
    Next
    INDEX
    Explanations

    names related to the Mahayana Buddhist tradition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    68
    +0.17
    0.6%
    351
    +0.15
    0.5%
    240
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.10
    232
    +0.15
    0.06
    326
    +0.14
    0.08
    Negative Logits
    DragonMagazine
    -0.99
    PORT
    -0.97
    estern
    -0.95
    chnology
    -0.90
    ACTED
    -0.88
     Anaheim
    -0.86
    ICE
    -0.84
    ffect
    -0.83
    CLUS
    -0.82
     dividing
    -0.82
    POSITIVE LOGITS
    itary
    1.21
    agara
    1.19
    onest
    1.15
    oku
    1.13
    ibaba
    1.10
    ority
    1.09
    eki
    1.09
    omed
    1.04
    omon
    1.03
    itates
    1.02
    Activations Density 1.112%

    No Known Activations