© 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. 24345
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or belonging

    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
    36
    +0.13
    0.7%
    230
    +0.13
    0.7%
    119
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.10
    271
    +0.13
    0.03
    156
    +0.12
    0.06
    Negative Logits
    rez
    -1.53
    ructions
    -1.40
    uxe
    -1.37
    ifice
    -1.36
    iere
    -1.36
    ctrine
    -1.34
     controllers
    -1.34
     flows
    -1.33
     controller
    -1.32
    CNT
    -1.32
    POSITIVE LOGITS
    ¿½
    2.51
    ĸ´
    1.87
     grave
    1.84
    Ļª
    1.64
    quier
    1.57
    Ĥ¬
    1.56
     unknown
    1.53
     clothing
    1.51
    ł
    1.49
    ĨĴ
    1.48
    Activations Density 0.293%

    No Known Activations