© 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. 35630
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to trades, contracts, and negotiations in sports

    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
    +0.22
    0.9%
    575
    +0.12
    0.5%
    463
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.22
    0.14
    543
    +0.12
    0.07
    531
    +0.10
    0.06
    Negative Logits
    isan
    -0.85
    alach
    -0.82
    iary
    -0.81
    aum
    -0.78
    jac
    -0.77
    andi
    -0.77
    osate
    -0.77
    entimes
    -0.76
    ebin
    -0.75
    english
    -0.74
    POSITIVE LOGITS
     deadline
    1.00
     kicker
    0.93
     Deadline
    0.84
     waivers
    0.81
     acquisitions
    0.79
     bait
    0.77
    able
    0.76
     negotiations
    0.71
     negotiation
    0.71
     proposal
    0.70
    Activations Density 7.891%

    No Known Activations