© 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. 1-RES-SM
    11. 29539
    Prev
    Next
    INDEX
    Explanations

    terms related to rendering processes in programming

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    188
    +0.13
    0.7%
    156
    +0.12
    0.7%
    180
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.13
    0.02
    188
    +0.12
    0.02
    180
    +0.12
    0.01
    Negative Logits
    yler
    -1.63
    neh
    -1.59
    rose
    -1.45
    ty
    -1.42
    xa
    -1.42
    ori
    -1.42
    âĪĹâĪĹ
    -1.41
    lla
    -1.41
    rin
    -1.40
    ffer
    -1.38
    POSITIVE LOGITS
    ings
    1.89
    ·¸
    1.87
    ERTY
    1.62
     journalism
    1.53
    ¹
    1.51
    geries
    1.50
    ontal
    1.49
     públic
    1.44
    itories
    1.43
    ĵ
    1.43
    Activations Density 0.100%

    No Known Activations