© 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. 27424
    Prev
    Next
    INDEX
    Explanations

    references to progress or improvement in various 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
    365
    +0.18
    1.0%
    392
    +0.15
    0.8%
    93
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.18
    0.03
    392
    +0.15
    0.03
    93
    +0.13
    0.03
    Negative Logits
    §
    -2.19
    ĻĤ
    -2.11
    Ľ
    -1.95
    ĥ½
    -1.90
    anus
    -1.89
    Ĵ
    -1.88
    ¿
    -1.87
    agra
    -1.80
    Ļª
    -1.77
    mina
    -1.74
    POSITIVE LOGITS
    ally
    2.71
     projects
    2.12
     stages
    1.85
    ial
    1.81
    ifically
    1.63
    emis
    1.62
     goals
    1.60
    ially
    1.57
     project
    1.57
     centers
    1.56
    Activations Density 0.103%

    No Known Activations