© 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 EvalsExportsinterp-engineNEWAPI 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. 35558
    Prev
    Next
    INDEX
    Explanations

    information related to specific video game consoles and platforms

    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
    447
    +0.20
    0.8%
    288
    +0.10
    0.4%
    508
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.20
    0.10
    343
    +0.10
    0.08
    464
    +0.10
    0.08
    Negative Logits
    atories
    -0.87
     scient
    -0.82
    atory
    -0.81
    bek
    -0.81
    atorium
    -0.79
     Faul
    -0.73
    struct
    -0.71
    athering
    -0.70
    nel
    -0.69
    natureconservancy
    -0.68
    POSITIVE LOGITS
     consoles
    1.03
     SLI
    1.01
    Xbox
    1.00
     emulator
    0.92
     Gamer
    0.92
     Accessories
    0.91
     Adapter
    0.86
     cartridges
    0.86
     peripher
    0.85
     Wii
    0.84
    Activations Density 11.461%

    No Known Activations