© 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. 29706
    Prev
    Next
    INDEX
    Explanations

    array and list structures in code

    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
    392
    +0.16
    0.9%
    302
    +0.12
    0.7%
    165
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.04
    271
    +0.12
    0.01
    17
    +0.11
    0.02
    Negative Logits
    ¿½
    -1.58
    specified
    -1.54
    tons
    -1.51
    Ń
    -1.50
    antly
    -1.49
    abad
    -1.49
    ously
    -1.45
     another
    -1.44
    points
    -1.44
    ic
    -1.43
    POSITIVE LOGITS
     tense
    1.62
    plist
    1.62
     closet
    1.51
     decir
    1.45
    ureus
    1.44
    lez
    1.41
    ansion
    1.38
    +)
    1.34
     milit
    1.32
    html
    1.31
    Activations Density 0.227%

    No Known Activations