© 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. 2-RES-SM
    11. 13117
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and phrases related to biological species and their attributes

    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
    360
    +0.14
    0.8%
    32
    +0.13
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.03
    366
    +0.13
    0.04
    32
    +0.12
    0.02
    Negative Logits
     delegate
    -1.94
    zbollah
    -1.80
     session
    -1.76
     savings
    -1.76
     sessions
    -1.70
     multiplier
    -1.68
    iseconds
    -1.67
    inees
    -1.67
     pay
    -1.61
     slots
    -1.60
    POSITIVE LOGITS
     Species
    2.71
     species
    2.31
    idae
    2.29
     clade
    2.20
    ĻĤ
    2.18
     genus
    2.13
     genera
    2.12
    aceae
    2.08
     taxonomic
    2.07
    species
    2.07
    Activations Density 0.472%

    No Known Activations