© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 13613
    Prev
    Next
    INDEX
    Explanations

    specific terms related to biology and scientific terminology

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    302
    +0.19
    1.1%
    320
    +0.18
    1.1%
    17
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.19
    0.09
    320
    +0.18
    0.10
    346
    +0.17
    0.08
    Negative Logits
    Ļª
    -3.62
    ľ
    -3.48
    Ĥ
    -3.47
    ¸
    -3.42
    Ŀ
    -3.40
    ©
    -3.23
    ĭ
    -3.22
    ŀ
    -3.19
    ¿½
    -3.19
    ģ
    -3.18
    POSITIVE LOGITS
    INESS
    1.54
    uple
    1.44
     stance
    1.40
     roll
    1.35
     sides
    1.35
     difference
    1.35
     Crick
    1.34
    CUSSION
    1.33
     stack
    1.31
     stature
    1.29
    Activations Density 2.545%

    No Known Activations