© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31340
    Prev
    Next
    INDEX
    Explanations

    phrases related to real estate and home buying

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    0.9%
    152
    +0.12
    0.5%
    218
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.21
    0.04
    614
    +0.12
    0.03
    685
    +0.12
    -0.01
    Negative Logits
     Paste
    -0.78
    uality
    -0.76
    DragonMagazine
    -0.76
    REDACTED
    -0.74
    =-=-=-=-=-=-=-=-
    -0.69
    aneous
    -0.68
     squid
    -0.67
     paraly
    -0.67
     pus
    -0.67
     secretion
    -0.64
    POSITIVE LOGITS
    chool
    1.21
    mort
    1.03
    buy
    1.01
    wright
    0.97
    builder
    0.95
     mortgages
    0.94
    owner
    0.90
    pun
    0.89
     foreclosure
    0.88
     Mortgage
    0.87
    Activations Density 12.678%

    No Known Activations