© 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. 24255
    Prev
    Next
    INDEX
    Explanations

    LaTeX command syntax and structure

    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
    31
    +0.17
    0.9%
    227
    +0.12
    0.7%
    148
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.17
    0.07
    129
    +0.12
    0.02
    204
    +0.12
    0.06
    Negative Logits
    achus
    -1.79
     stake
    -1.60
    elian
    -1.56
     opposite
    -1.53
    iture
    -1.53
    breaker
    -1.52
    ette
    -1.52
    ieri
    -1.49
     analyst
    -1.43
    illery
    -1.42
    POSITIVE LOGITS
    ĻĤ
    3.15
    «
    2.41
    ²
    2.39
    ½
    2.29
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.28
    ÃĥÃĤÃĥÃĤ
    2.24
    Ĥ¬
    2.22
    Į
    2.17
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.16
    Ľ
    2.15
    Activations Density 0.658%

    No Known Activations