© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    structured data within computer programming code

    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
    330
    +0.14
    0.5%
    148
    +0.12
    0.5%
    716
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.14
    0.10
    517
    +0.12
    0.09
    304
    +0.12
    0.09
    Negative Logits
    ISON
    -0.79
    ONSORED
    -0.72
    \\\\\\\\
    -0.71
    2020
    -0.71
    Ö
    -0.69
    atform
    -0.69
    ISION
    -0.69
    éŃĶ
    -0.69
     itself
    -0.66
     Dhabi
    -0.66
    POSITIVE LOGITS
     themselves
    1.04
    ettings
    1.03
    were
    1.00
    poons
    0.94
     aren
    0.89
     abound
    0.89
    selves
    0.89
    hops
    0.89
    ensitive
    0.88
     collectively
    0.88
    Activations Density 5.110%

    No Known Activations