© 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. 30906
    Prev
    Next
    INDEX
    Explanations

    references to organizations and institutes related to research and academia

    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
    98
    +0.18
    1.0%
    12
    +0.12
    0.7%
    92
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.18
    0.09
    248
    +0.12
    0.07
    285
    +0.11
    0.07
    Negative Logits
     against
    -1.86
    <-
    -1.72
    inally
    -1.71
    Unmarshal
    -1.68
    itical
    -1.68
    inous
    -1.62
     inflicted
    -1.62
    ulative
    -1.51
    against
    -1.49
    hth
    -1.48
    POSITIVE LOGITS
     Institute
    2.00
     Suite
    1.84
     Instit
    1.81
     Laboratory
    1.75
     Fellowship
    1.73
     Imaging
    1.71
     Univers
    1.71
     Graduate
    1.70
     University
    1.64
     Branch
    1.64
    Activations Density 0.671%

    No Known Activations