© 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 Local
    9. 6-RES_SCL-AJT
    11. 33682
    Prev
    Next
    INDEX
    Explanations

    references to looking back or reflecting on past events or memories

    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
    488
    +0.15
    0.6%
    447
    +0.13
    0.5%
    765
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.15
    0.08
    242
    +0.13
    0.06
    660
    +0.12
    0.05
    Negative Logits
     viz
    -0.87
     Hague
    -0.78
    ises
    -0.72
    icular
    -0.71
    ijn
    -0.70
     Ukrain
    -0.68
    entric
    -0.68
     Penguins
    -0.67
     pollut
    -0.67
    BLIC
    -0.67
    POSITIVE LOGITS
     nostalg
    1.32
    wards
    1.15
    dated
    1.09
    packs
    1.03
    gam
    1.00
    stab
    0.99
    trace
    0.99
    glass
    0.92
    WARD
    0.90
     fond
    0.90
    Activations Density 5.510%

    No Known Activations