© 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. 13192
    Prev
    Next
    INDEX
    Explanations

    the word "here"

    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
    127
    +0.13
    0.7%
    119
    +0.12
    0.7%
    250
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.13
    0.03
    250
    +0.12
    0.04
    127
    +0.12
    0.04
    Negative Logits
    §
    -4.11
    ľ
    -4.08
    ¬
    -4.05
    Ĩ
    -4.04
    ŀ
    -4.00
    Ħ
    -3.92
    ľĵ
    -3.87
    ĺ
    -3.87
    Ļª
    -3.86
    Ĥ¬
    -3.86
    POSITIVE LOGITS
    abouts
    2.89
    tics
    2.29
    bbe
    1.94
    upon
    1.69
    alc
    1.58
     behold
    1.58
    :&
    1.58
     clar
    1.56
    gom
    1.54
    psis
    1.50
    Activations Density 0.106%

    No Known Activations