© 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. 1-RES-SM
    11. 28335
    Prev
    Next
    INDEX
    Explanations

    criteria and objectives related to educational programs and outcomes

    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
    417
    +0.11
    0.6%
    164
    +0.11
    0.6%
    53
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.20
    271
    +0.11
    0.02
    17
    +0.10
    0.08
    Negative Logits
    «
    -2.96
    ¿½
    -2.83
    Į
    -2.65
    ĨĴ
    -2.47
    Ļ
    -2.40
    µ
    -2.39
    ļ
    -2.32
    ħ
    -2.31
    ĺ
    -2.25
    ij
    -2.23
    POSITIVE LOGITS
    "`
    1.53
    while
    1.38
    ytes
    1.36
     slaves
    1.35
    \"
    1.33
     fact
    1.33
     unless
    1.31
     disposable
    1.31
    1.31
     umbilical
    1.31
    Activations Density 2.368%

    No Known Activations