© 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. 37008
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political issues, especially regarding court decisions and governmental actions

    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
    152
    +0.13
    0.5%
    357
    +0.12
    0.5%
    146
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.16
    357
    +0.12
    0.11
    146
    +0.12
    0.11
    Negative Logits
    lets
    -0.95
    versions
    -0.89
     nick
    -0.87
    cephal
    -0.84
    sticks
    -0.81
    zbollah
    -0.76
    esters
    -0.76
    kick
    -0.76
    quickShipAvailable
    -0.75
    mobi
    -0.73
    POSITIVE LOGITS
     Constitution
    1.23
     Citizenship
    1.21
     Marshal
    1.18
     Attorney
    1.17
    GI
    1.15
     Cellular
    1.14
     Postal
    1.06
     Department
    1.02
     Tire
    1.01
     Treasury
    0.99
    Activations Density 8.028%

    No Known Activations