© 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. 26874
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures

    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
    156
    +0.18
    1.0%
    369
    +0.14
    0.7%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.18
    0.05
    307
    +0.14
    0.04
    374
    +0.12
    0.03
    Negative Logits
    iness
    -1.67
    izza
    -1.65
     oxidase
    -1.62
    àµį
    -1.62
    иÑĩеÑģк
    -1.53
     needs
    -1.52
    ulence
    -1.51
     behavior
    -1.50
    nip
    -1.47
    icity
    -1.47
    POSITIVE LOGITS
    ĺ
    2.63
    Ŀ
    2.55
    ¾
    2.40
    Ĵ
    2.29
    ł
    2.24
    ĨĴ
    2.23
    ħ
    2.16
    ²
    2.15
    µ
    2.12
    ½
    2.04
    Activations Density 0.234%

    No Known Activations