© 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 EvalsExportsAPI 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. 26125
    Prev
    Next
    INDEX
    Explanations

    occurrences of curly braces indicating structured data formats

    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
    478
    +0.19
    1.1%
    274
    +0.17
    1.0%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.19
    0.05
    175
    +0.17
    0.04
    38
    +0.11
    0.04
    Negative Logits
    (
    -1.53
    /%
    -1.50
    uation
    -1.50
     ?
    -1.47
     inception
    -1.41
    ape
    -1.40
    aling
    -1.39
     deprivation
    -1.38
    ually
    -1.37
     around
    -1.37
    POSITIVE LOGITS
    wasysym
    2.39
    amsbsy
    2.05
    Ļª
    2.04
    mathrsfs
    1.99
    ĥ½
    1.98
    amssymb
    1.91
    Į
    1.91
    ↵
    1.87
    1.87
    ↵
    1.87
    Activations Density 0.129%

    No Known Activations