© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11555
    Prev
    Next
    INDEX
    Explanations

    items related to devices, apparatuses, and their components in a technical 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    398
    +0.13
    0.7%
    83
    +0.11
    0.6%
    441
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.13
    0.00
    189
    +0.11
    0.02
    398
    +0.11
    0.01
    Negative Logits
    -4.57
    ↵
    -4.57
    ↵↵
    -4.57
    ↵            ↵
    -4.57
    <|outofrange|>
    -4.57
    <|outofrange|>
    -4.57
    ↵
    -4.57
    ↵
    -4.57
    ↵↵
    -4.57
    -4.57
    POSITIVE LOGITS
     disclosed
    2.66
     comprising
    2.61
    ""
    2.60
     wherein
    2.37
     capable
    2.24
     conventionally
    2.20
     utilizing
    2.20
     equipped
    2.18
     having
    2.13
     such
    2.13
    Activations Density 0.079%

    No Known Activations