© 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. 1-RES-SM
    11. 29261
    Prev
    Next
    INDEX
    Explanations

    terms related to biological colonies or groups, particularly in scientific contexts

    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
    156
    +0.18
    1.1%
    93
    +0.15
    0.9%
    43
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.18
    0.04
    271
    +0.15
    -0.00
    413
    +0.14
    0.01
    Negative Logits
    ĵ
    -3.61
    ¾
    -3.46
    »¿
    -3.46
    Ĥ¬
    -3.40
    Ĵ
    -3.39
    Ľ
    -3.39
    į
    -3.35
    ĸ
    -3.34
    ĩ
    -3.33
    ¼
    -3.30
    POSITIVE LOGITS
    aterial
    1.74
    break
    1.72
    inqu
    1.69
    icity
    1.65
    oning
    1.64
    ellar
    1.64
    isol
    1.61
    ient
    1.57
    apon
    1.54
    racted
    1.53
    Activations Density 0.254%

    No Known Activations