© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11869
    Prev
    Next
    INDEX
    Explanations

    codes and programming-related terms

    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
    447
    +0.20
    0.7%
    363
    +0.15
    0.5%
    107
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.20
    0.01
    326
    +0.15
    0.15
    176
    +0.14
    0.07
    Negative Logits
    icter
    -1.07
    halla
    -1.07
    obyl
    -1.01
     sclerosis
    -0.94
    risome
    -0.93
    isson
    -0.90
    vre
    -0.89
    awei
    -0.87
    ÄŁ
    -0.86
    aukee
    -0.85
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.84
    00000
    0.84
    Ö¼
    0.83
    cap
    0.82
    OPE
    0.81
    OOK
    0.81
    ĵ
    0.79
    edit
    0.79
    ŀ
    0.79
    é¾į
    0.78
    Activations Density 3.606%

    No Known Activations