© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 881
    Prev
    Next
    INDEX
    Explanations

    mentions related to real estate marketing and design tactics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    79
    +0.11
    0.5%
    705
    +0.11
    0.5%
    322
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.03
    665
    +0.11
    0.13
    570
    +0.10
    0.03
    Negative Logits
    leted
    -0.71
    ãĥ©ãĥ³
    -0.65
    hai
    -0.64
     proverb
    -0.62
     Dimension
    -0.61
     sandwic
    -0.58
    JM
    -0.58
    JO
    -0.55
     Assignment
    -0.55
     reminds
    -0.55
    POSITIVE LOGITS
     anymore
    1.66
     nor
    1.48
     anything
    1.31
     whatsoever
    1.27
     anywhere
    1.27
     any
    1.26
     anybody
    1.18
     anyone
    1.10
     slightest
    1.05
    nor
    1.02
    Activations Density 5.482%

    No Known Activations