© 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. 31139
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and social connections

    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
    186
    +0.20
    1.2%
    326
    +0.14
    0.8%
    282
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.25
    156
    +0.14
    0.27
    71
    +0.14
    0.26
    Negative Logits
    }</
    -1.48
    plain
    -1.45
    forth
    -1.44
     yourself
    -1.44
    ubot
    -1.44
     depending
    -1.43
    \%$
    -1.43
    CDATA
    -1.39
     onset
    -1.36
     Pradesh
    -1.36
    POSITIVE LOGITS
    iances
    1.45
     Official
    1.29
    wagen
    1.27
    Party
    1.24
    ==
    1.22
     bargain
    1.22
    tera
    1.20
    fficients
    1.19
    pocket
    1.18
    Availability
    1.18
    Activations Density 5.341%

    No Known Activations