© 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. 27262
    Prev
    Next
    INDEX
    Explanations

    terms related to packaging or bundled items

    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
    115
    +0.12
    0.7%
    156
    +0.12
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.12
    0.03
    173
    +0.12
    0.02
    448
    +0.12
    0.01
    Negative Logits
    §
    -2.14
     vain
    -2.12
    Ń
    -1.92
    ¶
    -1.91
    ·
    -1.81
    ¡
    -1.80
    ¯
    -1.79
    ¦
    -1.72
    ±
    -1.63
     possible
    -1.61
    POSITIVE LOGITS
    eners
    2.33
    ings
    2.15
    ackage
    2.13
    ups
    2.00
    estine
    1.97
    iness
    1.97
    aging
    1.93
    enger
    1.91
    ettes
    1.90
    worm
    1.90
    Activations Density 0.333%

    No Known Activations