© 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. 29541
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities in various contexts

    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
    369
    +0.23
    1.3%
    23
    +0.15
    0.9%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.23
    0.02
    369
    +0.15
    0.05
    439
    +0.11
    0.03
    Negative Logits
    auge
    -1.54
    Pub
    -1.53
     ().
    -1.47
    ernel
    -1.47
    eting
    -1.45
    "}\].
    -1.44
    microsoft
    -1.42
    ortex
    -1.42
    doms
    -1.41
    /"
    -1.39
    POSITIVE LOGITS
    immune
    1.54
     investigators
    1.45
    etta
    1.44
    onas
    1.41
    ologists
    1.40
     veins
    1.37
     markedly
    1.36
     researchers
    1.36
     dear
    1.35
    >(
    1.32
    Activations Density 1.728%

    No Known Activations