© 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. 28623
    Prev
    Next
    INDEX
    Explanations

    mentions of speakers and audio devices

    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
    156
    +0.22
    1.2%
    247
    +0.12
    0.7%
    82
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.22
    0.11
    156
    +0.12
    0.07
    271
    +0.11
    0.04
    Negative Logits
    ĥ½
    -3.20
    ¸
    -2.42
    ·
    -2.29
    ĺ
    -2.00
    ¤
    -1.97
    ĻĤ
    -1.94
    Ł
    -1.91
    ´
    -1.85
    ©
    -1.84
    °
    -1.84
    POSITIVE LOGITS
    phone
    2.14
    phones
    1.78
    mouth
    1.64
    scape
    1.63
    ius
    1.60
    card
    1.57
    们
    1.57
    ault
    1.55
    /#
    1.52
     speakers
    1.52
    Activations Density 0.459%

    No Known Activations