© 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. 2-RES-SM
    11. 13838
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    97
    +0.13
    0.7%
    508
    +0.13
    0.7%
    460
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.13
    0.00
    440
    +0.13
    0.00
    135
    +0.13
    0.00
    Negative Logits
    Ħ
    -4.02
    Ń
    -4.01
    ĩ
    -3.97
    µ
    -3.88
    «
    -3.80
    ·
    -3.73
    ij
    -3.72
    ¨
    -3.69
    IJ
    -3.63
    ³
    -3.63
    POSITIVE LOGITS
    rile
    1.60
    shire
    1.45
    cules
    1.42
    icer
    1.41
    ',
    1.40
     pictures
    1.40
    cases
    1.39
     pans
    1.38
    '.
    1.38
    '),
    1.38
    Activations Density 0.000%

    No Known Activations