© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26347
    Prev
    Next
    INDEX
    Explanations

    timestamps and date-related information

    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
    240
    +0.17
    1.0%
    293
    +0.13
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.17
    0.10
    85
    +0.13
    0.05
    220
    +0.12
    0.06
    Negative Logits
    ')$
    -1.58
    /)
    -1.57
    otry
    -1.54
    /#
    -1.52
    vez
    -1.52
    icos
    -1.50
     yer
    -1.48
    tera
    -1.47
    ?'
    -1.45
    /'
    -1.44
    POSITIVE LOGITS
    IJ
    2.39
    Ļª
    2.31
    ħ
    2.20
    ¦
    2.12
    ģ
    2.09
    ĻĤ
    2.07
    Ĭ
    2.04
    ŀ
    2.04
    Ĵ
    2.02
    ·¸
    2.00
    Activations Density 4.093%

    No Known Activations