© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6424
    Prev
    Next
    INDEX
    Explanations

    terms related to indie game developers, indie games, and gaming industry controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    295
    +0.13
    0.5%
    86
    +0.12
    0.4%
    211
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.17
    326
    +0.12
    0.13
    343
    +0.11
    0.06
    Negative Logits
    hammad
    -0.96
    istries
    -0.94
     imperson
    -0.90
    jri
    -0.87
     srfAttach
    -0.86
    mong
    -0.86
    xual
    -0.85
    racial
    -0.85
    atility
    -0.83
     appliances
    -0.82
    POSITIVE LOGITS
    Games
    1.20
     Ubisoft
    1.08
     Norn
    1.07
    ãĥ´
    1.07
    hesda
    1.05
     Games
    1.04
    isoft
    1.01
    venture
    1.00
     Enix
    0.99
     Blizzard
    0.98
    Activations Density 2.656%

    No Known Activations