© 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 EvalsExportsAPI 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. 26070
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and analysis in various fields

    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
    369
    +0.16
    0.9%
    348
    +0.13
    0.7%
    448
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.16
    0.07
    348
    +0.13
    0.11
    2
    +0.12
    0.10
    Negative Logits
     longer
    -1.60
    ptions
    -1.49
    plasia
    -1.44
    rs
    -1.44
    STEM
    -1.44
    ooting
    -1.44
    ensation
    -1.40
    schem
    -1.39
    eeper
    -1.39
    erty
    -1.35
    POSITIVE LOGITS
    ®
    4.53
    °
    4.32
    ↵
    4.31
    ↵
    4.31
    ↵
    4.31
    ↵↵
    4.31
    ↵↵
    4.31
    4.31
    4.31
    4.31
    Activations Density 2.374%

    No Known Activations