© 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. 13987
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and algorithms

    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
    17
    +0.24
    1.4%
    240
    +0.14
    0.8%
    301
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.24
    0.10
    17
    +0.14
    -0.00
    301
    +0.14
    0.07
    Negative Logits
    ĻĤ
    -2.93
    Ŀ
    -2.77
    º
    -2.72
    ¤
    -2.58
    ²
    -2.53
    ĩ
    -2.46
    ħ
    -2.45
    ¿½
    -2.44
    Ī
    -2.43
    ¹
    -2.40
    POSITIVE LOGITS
     coordinates
    1.64
    hores
    1.59
     located
    1.48
    erved
    1.47
    :/
    1.45
    omen
    1.40
    wind
    1.37
     HREF
    1.37
    gered
    1.35
    vered
    1.31
    Activations Density 3.246%

    No Known Activations