© 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 EvalsExportsAPI 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. 26368
    Prev
    Next
    INDEX
    Explanations

    references to licenses and terms related to software distribution

    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
    478
    +0.16
    0.9%
    98
    +0.13
    0.7%
    265
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.16
    0.02
    252
    +0.13
    0.02
    265
    +0.12
    0.02
    Negative Logits
    °
    -2.75
    ²
    -2.45
    ħ
    -2.41
    »¿
    -2.41
    Ŀ
    -2.38
    į
    -2.36
    ģ
    -2.32
    ī
    -2.25
    ĺ
    -2.22
    Į
    -2.20
    POSITIVE LOGITS
     your
    1.59
     GNU
    1.58
     latter
    1.50
     yourself
    1.41
     affiliates
    1.41
     moderation
    1.40
     CAT
    1.40
     activities
    1.38
     yours
    1.38
    TRODUCTION
    1.37
    Activations Density 0.188%

    No Known Activations