© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    phrases related to background information or personal history

    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
    393
    +0.09
    0.6%
    362
    +0.08
    0.5%
    608
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.09
    0.12
    669
    +0.08
    0.08
    362
    +0.07
    0.09
    Negative Logits
    DragonMagazine
    -0.54
    gey
    -0.54
    ndum
    -0.52
     cheered
    -0.51
    ubi
    -0.50
    gee
    -0.50
    ilet
    -0.49
     knocked
    -0.48
    enery
    -0.47
    ulia
    -0.47
    POSITIVE LOGITS
     curiosity
    0.63
     profound
    0.62
     tradition
    0.61
     conscience
    0.59
     secrecy
    0.58
     ambition
    0.57
     passion
    0.57
     conviction
    0.57
     dogma
    0.56
     bureaucracy
    0.56
    Activations Density 1.407%

    No Known Activations