© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 13862
    Prev
    Next
    INDEX
    Explanations

    words related to meditation, concentration, and mindfulness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.17
    0.7%
    659
    +0.15
    0.7%
    163
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.17
    0.07
    335
    +0.15
    0.07
    251
    +0.11
    0.06
    Negative Logits
    ãĥ´ãĤ¡
    -0.84
    IUM
    -0.69
     Carrier
    -0.68
     compe
    -0.66
     IRA
    -0.66
     Creed
    -0.65
     Fargo
    -0.65
    doors
    -0.64
     Metall
    -0.64
     Staples
    -0.64
    POSITIVE LOGITS
    anky
    1.28
    igsaw
    1.28
    umbled
    1.27
    ingle
    1.27
    agged
    1.25
    ourn
    1.23
    ammers
    1.20
    umper
    1.18
    itsu
    1.16
    umbo
    1.16
    Activations Density 6.266%

    No Known Activations