© 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. 29275
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching and querying for information

    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
    +0.26
    1.5%
    170
    +0.15
    0.9%
    111
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.26
    0.20
    271
    +0.15
    0.09
    156
    +0.15
    0.10
    Negative Logits
    ·¸
    -2.15
    ´
    -2.09
    <|outofrange|>
    -1.92
    ↵
    -1.92
    -1.92
    -1.92
    -1.92
    -1.92
    -1.92
    ↵
    -1.92
    POSITIVE LOGITS
     books
    1.73
    aments
    1.62
    noreply
    1.47
    pocket
    1.46
    agraph
    1.42
    blogger
    1.41
    shots
    1.38
    optera
    1.36
    cue
    1.30
    ental
    1.30
    Activations Density 0.375%

    No Known Activations