© 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. 27377
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating relationships or connections

    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
    381
    +0.13
    0.7%
    454
    +0.13
    0.7%
    172
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.13
    0.02
    381
    +0.13
    0.01
    391
    +0.12
    0.01
    Negative Logits
     walls
    -1.77
     plaques
    -1.73
    iscus
    -1.69
    rente
    -1.64
    flies
    -1.55
     fronts
    -1.55
     moss
    -1.54
    bourg
    -1.54
    lessness
    -1.52
    waters
    -1.52
    POSITIVE LOGITS
    eligible
    1.74
     least
    1.49
     obtaining
    1.45
     applicable
    1.44
    fit
    1.39
    redited
    1.36
     satisfied
    1.36
     exec
    1.36
     remotely
    1.36
     choosing
    1.35
    Activations Density 0.170%

    No Known Activations