© 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. 25621
    Prev
    Next
    INDEX
    Explanations

    specific scientific measurements or numeric data

    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
    189
    +0.13
    0.7%
    160
    +0.12
    0.7%
    84
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.13
    0.01
    98
    +0.12
    -0.01
    136
    +0.12
    -0.01
    Negative Logits
    ¿½
    -2.88
    ĻĤ
    -2.75
    ĺ
    -2.68
      ↵
    -2.65
    -2.65
    -2.65
    <|outofrange|>
    -2.65
    -2.65
    -2.65
    -2.65
    POSITIVE LOGITS
     herself
    1.54
    journal
    1.53
    )](#
    1.51
     himself
    1.46
    abouts
    1.39
    chester
    1.38
    storm
    1.37
     somebody
    1.34
     something
    1.30
     Maybe
    1.28
    Activations Density 0.470%

    No Known Activations