© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10701
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams and their activities

    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
    313
    +0.17
    0.5%
    241
    +0.16
    0.5%
    686
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.17
    0.03
    406
    +0.16
    0.04
    611
    +0.15
    0.04
    Negative Logits
    leans
    -1.06
    axter
    -1.03
    etheless
    -0.97
    wegian
    -0.90
     sucker
    -0.90
     litter
    -0.89
    ategory
    -0.88
    alkyrie
    -0.88
    wen
    -0.87
     Kers
    -0.87
    POSITIVE LOGITS
    biz
    1.69
    case
    1.60
    cases
    1.52
    alter
    1.48
     Tycoon
    1.41
    downs
    1.36
    ings
    1.32
    rooms
    1.22
    oos
    1.22
    mable
    1.20
    Activations Density 0.507%

    No Known Activations