© 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. 2019
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and the aging process, specifically in the context of genetics and physiological changes

    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
    288
    +0.22
    0.7%
    110
    +0.20
    0.6%
    326
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.14
    326
    +0.20
    0.10
    110
    +0.17
    0.08
    Negative Logits
    ramid
    -1.29
    kell
    -1.26
    kie
    -1.15
    usha
    -1.09
    vati
    -1.09
    ilar
    -1.05
    ãĥīãĥ©
    -1.03
    orneys
    -1.02
    MN
    -1.00
    ª
    -1.00
    POSITIVE LOGITS
    escent
    1.30
     decay
    1.23
    gradation
    1.03
     decaying
    1.02
    span
    1.01
     dementia
    0.99
     plaque
    0.97
     aging
    0.97
     nostalg
    0.96
     sen
    0.96
    Activations Density 1.509%

    No Known Activations