© 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. 4-RES-SM
    11. 13845
    Prev
    Next
    INDEX
    Explanations

    code-related terms and patterns related to data communication and object management

    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
    307
    +0.29
    1.7%
    47
    +0.14
    0.8%
    282
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.29
    0.09
    240
    +0.14
    0.01
    157
    +0.10
    0.09
    Negative Logits
     myself
    -2.24
    laughs
    -1.86
    atrix
    -1.74
    my
    -1.72
    III
    -1.64
    OVA
    -1.59
    ailand
    -1.58
    ARE
    -1.57
    chaft
    -1.56
    raint
    -1.55
    POSITIVE LOGITS
    6.96
    ↵
    6.96
    <|outofrange|>
    6.96
    ↵
    6.96
    <|outofrange|>
    6.96
    ↵
    6.96
    6.96
     ↵
    6.96
    6.96
    ↵↵
    6.96
    Activations Density 1.835%

    No Known Activations