© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12370
    Prev
    Next
    INDEX
    Explanations

    references to authors or creators associated with works or licenses

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    34
    +0.13
    0.7%
    202
    +0.13
    0.7%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.13
    0.01
    443
    +0.13
    0.01
    34
    +0.11
    0.01
    Negative Logits
    chio
    -1.73
    nier
    -1.61
    pire
    -1.51
    ize
    -1.42
    ĻĤ
    -1.41
    izing
    -1.40
    elijk
    -1.35
     outdoors
    -1.34
    rient
    -1.33
     towards
    -1.31
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.56
     WARRANTY
    1.56
    иб
    1.46
    Ñĥж
    1.44
     IMPLIED
    1.41
    лем
    1.41
    еж
    1.40
    anding
    1.38
     Springer
    1.37
    еÑĩ
    1.36
    Activations Density 0.022%

    No Known Activations