© 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. 25256
    Prev
    Next
    INDEX
    Explanations

    percentage values in context

    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
    241
    +0.13
    0.7%
    115
    +0.12
    0.7%
    261
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.10
    271
    +0.12
    0.04
    156
    +0.10
    0.05
    Negative Logits
     named
    -1.70
    amps
    -1.66
    ette
    -1.47
     renamed
    -1.40
     Magnetic
    -1.35
    ĻĤ
    -1.33
    ij
    -1.31
    ivers
    -1.30
    ammed
    -1.29
     listed
    -1.28
    POSITIVE LOGITS
    heta
    1.71
     taste
    1.59
     surprise
    1.53
    hind
    1.52
    rost
    1.48
     duration
    1.47
    rogens
    1.45
    reira
    1.43
    dry
    1.42
    ^[@
    1.42
    Activations Density 0.399%

    No Known Activations