© 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. 12847
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer players and matches, particularly involving specific players like Klinsmann and events like World Cup competitions

    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
    526
    +0.15
    0.6%
    659
    +0.14
    0.5%
    48
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.05
    288
    +0.14
    0.07
    289
    +0.13
    0.01
    Negative Logits
    Interstitial
    -1.02
    ãģ®éŃĶ
    -1.00
    ãĥ¼ãĥĨãĤ£
    -0.90
    EMENT
    -0.89
    ITED
    -0.83
    TAIN
    -0.83
     spirited
    -0.82
    MODE
    -0.82
    IDENT
    -0.81
     FANTASY
    -0.80
    POSITIVE LOGITS
    assic
    1.29
    oser
    1.14
     Klux
    1.11
    azo
    1.05
    osing
    1.04
    owsky
    1.02
    ibrary
    1.02
    utz
    1.00
    avier
    0.99
    usk
    0.99
    Activations Density 0.908%

    No Known Activations