© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29848
    Prev
    Next
    INDEX
    Explanations

    references to physical locations or movements

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    366
    +0.18
    1.0%
    271
    +0.13
    0.7%
    409
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.18
    0.00
    34
    +0.13
    0.00
    43
    +0.11
    0.00
    Negative Logits
     ends
    -1.76
    ache
    -1.73
    ilage
    -1.62
    zie
    -1.56
    hart
    -1.48
    illion
    -1.46
    ade
    -1.43
    elson
    -1.42
    she
    -1.42
    hole
    -1.40
    POSITIVE LOGITS
    )];
    1.60
    :--
    1.47
    ]));
    1.40
    :**]{}
    1.38
    .]
    1.37
     Trip
    1.36
     indeed
    1.35
    ATCC
    1.34
    Relative
    1.34
    **](#
    1.31
    Activations Density 0.000%

    No Known Activations