© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 31185
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographical locations or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.46
    3.1%
    156
    +0.44
    3.0%
    63
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.46
    0.05
    111
    +0.44
    0.05
    4
    +0.12
    0.04
    Negative Logits
    paces
    -1.39
    ktop
    -1.32
     Declaration
    -1.28
     cathe
    -1.23
    babel
    -1.21
    itars
    -1.21
     map
    -1.20
    cessive
    -1.18
    hig
    -1.17
     bikes
    -1.15
    POSITIVE LOGITS
    être
    1.60
    ank
    1.51
    ples
    1.40
    atter
    1.34
     tone
    1.32
    vet
    1.28
    agra
    1.28
    ophy
    1.26
    laughs
    1.25
    orr
    1.23
    Activations Density 0.031%

    No Known Activations