© 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. 31949
    Prev
    Next
    INDEX
    Explanations

    mentions of size and dimensions in different 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/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
    173
    +0.12
    0.7%
    100
    +0.11
    0.6%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.12
    0.03
    361
    +0.11
    0.03
    217
    +0.11
    0.03
    Negative Logits
    ±
    -2.31
    ¾
    -2.16
    ĵ
    -2.13
    ľĵ
    -2.12
    ¼
    -2.03
    ¹
    -1.96
    º
    -1.96
    ·
    -1.96
    ¦
    -1.95
    ¿
    -1.90
    POSITIVE LOGITS
    ahead
    1.86
    etable
    1.86
    able
    1.86
     (\<
    1.68
     varies
    1.68
    etting
    1.67
    izable
    1.63
    ening
    1.59
    ened
    1.55
     (\>
    1.55
    Activations Density 0.127%

    No Known Activations