© 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 Local
    9. 6-RES_SCL-AJT
    11. 32464
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    +0.27
    1.1%
    459
    +0.12
    0.5%
    205
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.27
    0.12
    689
    +0.12
    0.14
    173
    +0.11
    0.11
    Negative Logits
     Coch
    -0.72
    Coll
    -0.72
    enter
    -0.71
     Faul
    -0.70
     Chimera
    -0.68
     Gat
    -0.66
    brand
    -0.66
     Cla
    -0.66
     Brist
    -0.64
    craft
    -0.63
    POSITIVE LOGITS
    âĢ²
    0.84
     accus
    0.79
    ASED
    0.74
    ourney
    0.73
     devote
    0.70
     Difficulty
    0.68
    itialized
    0.65
     spoil
    0.64
     disparate
    0.64
    dayName
    0.64
    Activations Density 13.420%

    No Known Activations