© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6070
    Prev
    Next
    INDEX
    Explanations

    directions or locations, specifically compass directions (north, south, east, west)

    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
    377
    +0.17
    0.5%
    565
    +0.16
    0.5%
    496
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.17
    0.06
    596
    +0.16
    0.05
    607
    +0.16
    0.05
    Negative Logits
    wcsstore
    -1.23
    ellation
    -1.23
    aminer
    -1.15
    anamo
    -1.09
     Mehran
    -1.07
    ulous
    -1.00
     MFT
    -1.00
    argon
    -0.99
    Information
    -0.97
     Injury
    -0.97
    POSITIVE LOGITS
    ward
    1.94
    wards
    1.53
    west
    1.39
    side
    1.39
     side
    1.25
    urst
    1.24
    bound
    1.24
     west
    1.21
     hemisphere
    1.17
     pole
    1.13
    Activations Density 0.638%

    No Known Activations