© 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. 36467
    Prev
    Next
    INDEX
    Explanations

    references to historical events or individuals

    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
    +0.19
    0.9%
    314
    +0.16
    0.7%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.19
    0.04
    154
    +0.16
    0.14
    446
    +0.11
    0.12
    Negative Logits
     Jiu
    -0.77
     SOC
    -0.74
     IMAGES
    -0.72
     FORM
    -0.69
     Date
    -0.68
     MSM
    -0.67
     LINE
    -0.65
     TRAN
    -0.64
     WM
    -0.63
    Round
    -0.63
    POSITIVE LOGITS
    eal
    1.04
    rik
    0.92
    ntil
    0.92
    ploy
    0.91
    tsy
    0.89
    aminer
    0.88
    acters
    0.88
    iffe
    0.87
    abor
    0.85
    antry
    0.85
    Activations Density 4.863%

    No Known Activations