© 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. 2-RES-SM
    11. 28148
    Prev
    Next
    INDEX
    Explanations

    references to board members and boards in various contexts

    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
    119
    +0.13
    0.8%
    156
    +0.12
    0.7%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.13
    0.03
    119
    +0.12
    0.01
    113
    +0.12
    0.02
    Negative Logits
    ©
    -2.47
    Ĥ
    -2.32
    ĥ½
    -2.30
    ĵ
    -2.22
    ¥
    -2.19
    Ĭ
    -2.12
    §
    -2.07
    ĩ
    -1.97
    ¯
    -1.95
    ı
    -1.91
    POSITIVE LOGITS
    ings
    2.21
    walk
    2.19
    ership
    2.13
    yard
    2.03
    holder
    2.00
    emann
    1.91
     members
    1.87
    esian
    1.86
    bie
    1.83
     chair
    1.83
    Activations Density 0.188%

    No Known Activations