© 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. 31109
    Prev
    Next
    INDEX
    Explanations

    references to wet environments, such as wetlands, rain, or a moist atmosphere

    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
    +0.18
    0.7%
    710
    +0.15
    0.6%
    459
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.18
    0.10
    70
    +0.15
    0.10
    250
    +0.14
    0.04
    Negative Logits
    allery
    -0.81
    vernment
    -0.78
    udic
    -0.75
     distingu
    -0.74
    verage
    -0.73
    CVE
    -0.72
     resemb
    -0.72
    */(
    -0.70
    士
    -0.70
    cffffcc
    -0.70
    POSITIVE LOGITS
    ting
    1.39
    ter
    1.21
    ness
    1.19
    ted
    1.14
    lock
    1.11
    ters
    1.10
    bag
    1.02
    nes
    1.01
     wet
    1.00
     nood
    1.00
    Activations Density 7.115%

    No Known Activations