© 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. 26072
    Prev
    Next
    INDEX
    Explanations

    specific key-value pairs associated with configuration settings

    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
    +0.18
    1.1%
    466
    +0.15
    0.9%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.18
    0.05
    100
    +0.15
    0.06
    165
    +0.13
    0.04
    Negative Logits
    ](
    -1.78
    \]](
    -1.69
    izing
    -1.45
    ization
    -1.40
    eti
    -1.39
    /](
    -1.39
     warrants
    -1.39
    '):
    -1.38
    ...](
    -1.37
    jer
    -1.37
    POSITIVE LOGITS
    ĥ½
    1.75
    bbe
    1.50
    ľĵ
    1.40
    uate
    1.39
     gradual
    1.39
    pone
    1.37
    uilt
    1.37
    ahan
    1.36
     pupils
    1.34
    ubicin
    1.31
    Activations Density 0.262%

    No Known Activations