© 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. 28909
    Prev
    Next
    INDEX
    Explanations

    code-related terms or tags

    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
    220
    +0.11
    0.7%
    12
    +0.10
    0.6%
    144
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.02
    425
    +0.10
    0.01
    180
    +0.10
    0.01
    Negative Logits
    icked
    -1.75
    appropri
    -1.71
    med
    -1.65
    OVE
    -1.60
     distracted
    -1.53
     matter
    -1.48
    omorphisms
    -1.46
     mustard
    -1.45
    ations
    -1.43
    WHERE
    -1.41
    POSITIVE LOGITS
    velopment
    2.24
    ÅĽci
    2.05
    gia
    1.98
    ository
    1.90
    wright
    1.89
    ictionary
    1.79
    amento
    1.78
    cano
    1.77
    garten
    1.77
    nals
    1.75
    Activations Density 0.131%

    No Known Activations