© 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. 24789
    Prev
    Next
    INDEX
    Explanations

    data structures and their definitions in programming context

    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
    47
    +0.20
    1.1%
    69
    +0.12
    0.6%
    136
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.20
    0.20
    136
    +0.12
    -0.08
    480
    +0.12
    0.08
    Negative Logits
    ´
    -2.73
    ĻĤ
    -2.41
    Ĩ
    -2.34
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.32
    Ĥ
    -2.30
    IJ
    -2.29
    <|outofrange|>
    -2.28
    č↵č↵
    -2.28
    <|outofrange|>
    -2.28
    -2.28
    POSITIVE LOGITS
    irections
    1.65
    ionale
    1.60
    isers
    1.46
    ].)
    1.45
    ?).
    1.35
    usk
    1.34
     Moscow
    1.32
    zez
    1.31
    :/
    1.31
    itories
    1.31
    Activations Density 5.645%

    No Known Activations