© 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. 27336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more."

    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
    374
    +0.13
    0.7%
    86
    +0.12
    0.7%
    231
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.03
    18
    +0.12
    0.03
    125
    +0.12
    0.02
    Negative Logits
    ľĵ
    -2.94
    ¹
    -2.46
    ¼
    -2.40
    ½
    -2.17
    ®
    -2.13
    ¾
    -2.10
    ij
    -2.09
    Ĥ¬
    -2.09
    £
    -2.07
    ¶
    -2.04
    POSITIVE LOGITS
     than
    2.71
    Than
    2.48
    than
    2.06
     Than
    1.73
     broadly
    1.65
     respects
    1.64
     caution
    1.60
     importantly
    1.56
    tro
    1.52
    irms
    1.52
    Activations Density 0.040%

    No Known Activations