© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    phrases related to claims or submissions in a structured context

    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
    323
    +0.15
    0.9%
    293
    +0.12
    0.7%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.26
    156
    +0.12
    0.27
    71
    +0.12
    0.26
    Negative Logits
    ¸
    -3.19
    «
    -3.16
    ¿½
    -3.16
    º
    -3.05
    ħ
    -3.00
    ĸ´
    -2.99
    Ń
    -2.98
    ·
    -2.95
    Ĥ
    -2.94
    »¿
    -2.94
    POSITIVE LOGITS
    noreply
    1.59
    AML
    1.45
    usters
    1.39
     KY
    1.39
    CDATA
    1.38
    ena
    1.33
     rd
    1.29
     ns
    1.29
    regnancy
    1.28
    ect
    1.27
    Activations Density 4.284%

    No Known Activations