© 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. 27799
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational processes and regulations

    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
    +0.47
    3.1%
    240
    +0.25
    1.6%
    400
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.47
    0.01
    418
    +0.25
    -0.01
    213
    +0.14
    0.07
    Negative Logits
    ÑĢÑĥг
    -1.63
    еж
    -1.51
    ÑĢоÑģ
    -1.47
    екÑĤ
    -1.43
    енÑĮ
    -1.43
    енÑĤ
    -1.37
    ап
    -1.36
    или
    -1.36
    олÑĮ
    -1.36
    eeper
    -1.34
    POSITIVE LOGITS
     versus
    1.53
    **.
    1.36
    -
    1.32
    uing
    1.30
     behaviour
    1.28
     welfare
    1.28
     vs
    1.27
    **:
    1.26
    helm
    1.24
    imal
    1.23
    Activations Density 1.881%

    No Known Activations