© 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. 3959
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware specifications

    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
    60
    +0.15
    0.6%
    325
    +0.14
    0.5%
    450
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.15
    -0.03
    620
    +0.14
    0.02
    326
    +0.13
    0.29
    Negative Logits
    avez
    -0.99
    vim
    -0.87
    uscript
    -0.87
    ocene
    -0.86
     Homeless
    -0.83
     Lester
    -0.82
    ibli
    -0.82
     Petr
    -0.81
     fle
    -0.81
     plural
    -0.81
    POSITIVE LOGITS
     GPUs
    1.64
     CPUs
    1.63
     GPU
    1.55
     chipset
    1.51
     processors
    1.49
     Nvidia
    1.41
     GDDR
    1.36
     overcl
    1.35
     cores
    1.34
     processor
    1.34
    Activations Density 16.425%

    No Known Activations