© 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. 36871
    Prev
    Next
    INDEX
    Explanations

    references to legal and governmental procedures and documentation

    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
    481
    +0.28
    1.5%
    447
    +0.13
    0.7%
    521
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.28
    0.32
    225
    +0.13
    0.10
    430
    +0.10
    0.19
    Negative Logits
    ashtra
    -0.65
    atonin
    -0.58
    Tracker
    -0.57
    phia
    -0.56
    ichick
    -0.56
    urat
    -0.56
    cients
    -0.55
    ruciating
    -0.55
    acci
    -0.55
    é»Ĵ
    -0.54
    POSITIVE LOGITS
    earances
    0.59
     Jury
    0.56
     Starg
    0.54
     Documents
    0.53
    hyde
    0.53
    atari
    0.52
     Warrant
    0.52
     Newsp
    0.52
     dign
    0.52
     ib
    0.50
    Activations Density 15.484%

    No Known Activations