© 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. 27818
    Prev
    Next
    INDEX
    Explanations

    technical terms or codes related to software and technology

    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
    406
    +0.13
    0.8%
    404
    +0.12
    0.7%
    130
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.02
    334
    +0.12
    0.02
    457
    +0.12
    0.02
    Negative Logits
    atically
    -1.69
    matically
    -1.59
    ontally
    -1.55
    Ł
    -1.54
    amycin
    -1.51
    okinetic
    -1.50
    ortion
    -1.48
    icon
    -1.48
    oint
    -1.48
    omi
    -1.44
    POSITIVE LOGITS
    FC
    1.56
    eries
    1.48
    FIL
    1.45
    NS
    1.44
    HR
    1.44
    ception
    1.40
    ÅĽ
    1.39
    LEV
    1.38
    TAIN
    1.37
    ENO
    1.36
    Activations Density 0.092%

    No Known Activations