© 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. 24915
    Prev
    Next
    INDEX
    Explanations

    mentions of URLs or links in the text

    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
    +0.21
    1.2%
    397
    +0.13
    0.7%
    17
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.21
    0.02
    91
    +0.13
    0.02
    397
    +0.10
    0.01
    Negative Logits
    urane
    -1.73
    ighter
    -1.65
    forth
    -1.61
    clusively
    -1.60
    cluding
    -1.58
    urers
    -1.57
    stitutional
    -1.52
     forth
    -1.49
    ifically
    -1.49
    doors
    -1.49
    POSITIVE LOGITS
    ://
    1.75
    AtIndex
    1.57
    ARGS
    1.53
    :/
    1.52
    Bs
    1.48
     inscription
    1.45
    BG
    1.42
     lookup
    1.42
    borne
    1.36
    maps
    1.35
    Activations Density 0.075%

    No Known Activations