© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11805
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to medical or biological studies

    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
    21
    +0.46
    3.8%
    450
    +0.12
    1.0%
    78
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.46
    0.21
    255
    +0.12
    0.00
    450
    +0.10
    0.07
    Negative Logits
    Ļª
    -1.57
     mine
    -1.16
     accordingly
    -1.15
     favour
    -1.14
    lessly
    -1.12
    ²
    -1.12
     slowly
    -1.11
     tack
    -1.08
    FFIRMED
    -1.08
    µ
    -1.08
    POSITIVE LOGITS
    unreadable
    1.13
    Ïķ
    1.13
    aeda
    1.10
    iston
    1.10
    lemental
    1.07
     Sox
    1.04
    glich
    1.03
    +)
    0.99
    aughter
    0.98
    ström
    0.98
    Activations Density 2.506%

    No Known Activations