© 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. 2736
    Prev
    Next
    INDEX
    Explanations

    phrases related to mediocrity and systems of oppression

    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
    616
    +0.12
    0.5%
    128
    +0.12
    0.5%
    707
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.12
    0.02
    291
    +0.12
    0.02
    174
    +0.11
    0.01
    Negative Logits
    ORGE
    -0.74
    ãģ¦
    -0.74
    STR
    -0.70
    ãģ®éŃĶ
    -0.69
     french
    -0.65
     Dahl
    -0.65
    enegger
    -0.65
    cember
    -0.64
    pler
    -0.64
    roads
    -0.63
    POSITIVE LOGITS
    acies
    1.27
    atically
    1.06
    ocr
    1.05
    anny
    0.89
    atics
    0.88
    ilic
    0.88
    isy
    0.87
    kefeller
    0.87
    ansky
    0.86
    ionage
    0.85
    Activations Density 0.126%

    No Known Activations