© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    codes and technical information related to technology and computer systems

    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
    640
    +0.54
    2.2%
    160
    +0.13
    0.5%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.54
    0.22
    160
    +0.13
    0.13
    179
    +0.12
    0.10
    Negative Logits
    hement
    -1.43
     awa
    -1.08
    aday
    -0.98
     undermin
    -0.94
     destro
    -0.92
    inois
    -0.90
    uggest
    -0.89
    agy
    -0.88
     veter
    -0.86
     experien
    -0.86
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.06
    ³³³³³³³³
    0.91
    ³³³
    0.86
    ................................
    0.85
     largeDownload
    0.84
    ãĥŁ
    0.81
    ALT
    0.79
    Synopsis
    0.78
    Folder
    0.78
    ergy
    0.78
    Activations Density 0.997%

    No Known Activations