© 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. 25469
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    203
    +0.14
    0.8%
    369
    +0.14
    0.8%
    6
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.20
    271
    +0.14
    0.08
    17
    +0.14
    0.12
    Negative Logits
    EventListener
    -1.53
    ogr
    -1.49
    urable
    -1.43
     flaw
    -1.43
    (@"
    -1.42
    ably
    -1.42
    etically
    -1.40
    semble
    -1.38
    ovir
    -1.38
    (<
    -1.35
    POSITIVE LOGITS
    zione
    1.77
     Muslim
    1.67
     Islam
    1.52
    fasterxml
    1.52
    wikipedia
    1.43
    href
    1.42
    own
    1.42
    romycin
    1.39
    requency
    1.38
    Muslim
    1.37
    Activations Density 0.713%

    No Known Activations