© 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. 27390
    Prev
    Next
    INDEX
    Explanations

    possessive forms and references to women

    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
    34
    +0.12
    0.7%
    456
    +0.11
    0.6%
    505
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.12
    0.03
    456
    +0.11
    0.04
    505
    +0.11
    0.04
    Negative Logits
    izard
    -1.63
     others
    -1.58
    down
    -1.53
    (){
    -1.51
    ankind
    -1.47
     converts
    -1.43
    pile
    -1.42
    (@"
    -1.42
    acteria
    -1.40
    parse
    -1.38
    POSITIVE LOGITS
    ¿½
    2.22
    ¾
    2.03
    ħ
    1.99
    ĥ
    1.80
    »¿
    1.80
    IJ
    1.72
    ª
    1.69
    Ļª
    1.69
     age
    1.66
    ²
    1.59
    Activations Density 0.240%

    No Known Activations