© 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. 25607
    Prev
    Next
    INDEX
    Explanations

    mentions of specific companies

    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
    156
    +0.25
    1.5%
    119
    +0.13
    0.7%
    367
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.25
    0.02
    367
    +0.13
    0.03
    271
    +0.11
    0.00
    Negative Logits
    ĥ½
    -1.67
    Ĥ
    -1.50
    Ĥ¬
    -1.49
     yours
    -1.44
    -1.44
    č↵
    -1.44
                  ↵
    -1.44
    -1.44
    ↵
    -1.44
    ↵
    -1.44
    POSITIVE LOGITS
    eren
    1.71
    house
    1.69
    fficients
    1.67
    agment
    1.64
    aceut
    1.63
     Arms
    1.62
    lement
    1.55
    nai
    1.53
    stown
    1.52
    gens
    1.52
    Activations Density 0.151%

    No Known Activations