© 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. 4-RES-SM
    11. 11056
    Prev
    Next
    INDEX
    Explanations

    references to UI components and their layouts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.18
    1.0%
    17
    +0.13
    0.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.18
    0.05
    255
    +0.13
    -0.00
    93
    +0.12
    0.03
    Negative Logits
    -3.63
     ↵
    -3.63
    <|outofrange|>
    -3.63
    ↵
    -3.63
     ↵
    -3.63
    -3.63
    -3.63
    č↵
    -3.63
    -3.63
    ↵↵
    -3.63
    POSITIVE LOGITS
    Delegate
    2.41
    Renderer
    2.10
    Layout
    2.08
    Holder
    2.02
    UI
    2.00
    Inflater
    1.96
    AtIndex
    1.92
    izer
    1.92
    ViewModel
    1.89
    UIT
    1.88
    Activations Density 0.372%

    No Known Activations