© 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. 3743
    Prev
    Next
    INDEX
    Explanations

    words related to mobile technology brands and products

    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
    121
    +0.07
    0.5%
    739
    +0.07
    0.5%
    320
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.07
    0.09
    585
    +0.07
    0.11
    294
    +0.07
    0.04
    Negative Logits
    icals
    -0.65
    orate
    -0.55
    glers
    -0.55
    opl
    -0.55
    代
    -0.54
    ibly
    -0.54
    neys
    -0.54
    å£
    -0.53
    ris
    -0.52
    metic
    -0.52
    POSITIVE LOGITS
     Suit
    0.62
     Collection
    0.52
     Panther
    0.51
     Packs
    0.50
     Stores
    0.49
    aucus
    0.48
     Practice
    0.48
     Rankings
    0.47
     Sounds
    0.47
     Madness
    0.47
    Activations Density 8.557%

    No Known Activations