© 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. 11383
    Prev
    Next
    INDEX
    Explanations

    words related to love and affection

    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
    608
    +0.16
    0.6%
    459
    +0.15
    0.5%
    161
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.04
    8
    +0.15
    0.05
    246
    +0.13
    0.05
    Negative Logits
    interstitial
    -1.13
    ulhu
    -1.04
    otomy
    -1.00
     reluct
    -0.99
    icter
    -0.99
    culosis
    -0.95
    urers
    -0.94
    raviolet
    -0.94
    TPPStreamerBot
    -0.93
    merce
    -0.92
    POSITIVE LOGITS
     dearly
    1.22
    fully
    1.20
     uncond
    1.18
    joy
    1.15
    birds
    1.08
     passionately
    1.07
    ably
    0.96
     Pwr
    0.95
    lihood
    0.93
    tta
    0.93
    Activations Density 0.833%

    No Known Activations