© 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. 7223
    Prev
    Next
    INDEX
    Explanations

    mentions or references to Russian President Vladimir Putin

    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
    311
    +0.22
    0.7%
    288
    +0.16
    0.5%
    569
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.22
    0.11
    288
    +0.16
    0.14
    430
    +0.14
    0.13
    Negative Logits
    agra
    -1.33
    nexus
    -1.22
    ramid
    -1.19
    ells
    -1.19
    arah
    -1.12
    apple
    -1.10
    ingham
    -1.06
    NetMessage
    -1.03
    iband
    -1.03
     sled
    -1.02
    POSITIVE LOGITS
     Putin
    1.30
     Tayyip
    1.28
    oulos
    1.25
     Rubio
    1.21
     Modi
    1.20
    CLASSIFIED
    1.20
     Fernandez
    1.19
     Vlad
    1.16
     Hud
    1.15
     Vernon
    1.15
    Activations Density 1.945%

    No Known Activations