© 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. 2-RES-SM
    11. 28900
    Prev
    Next
    INDEX
    Explanations

    occurrences of commas and periods in the text

    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
    74
    +0.11
    0.6%
    349
    +0.11
    0.6%
    186
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.11
    0.02
    74
    +0.11
    0.02
    253
    +0.10
    0.02
    Negative Logits
    ľĵ
    -1.74
    ,&
    -1.62
    onica
    -1.59
    (),
    -1.50
    »¿
    -1.47
    ↵
    -1.47
    č↵
    -1.47
    -1.47
    <|outofrange|>
    -1.47
    ↵
    -1.47
    POSITIVE LOGITS
    sible
    1.59
     Ãħ
    1.41
    ]{.
    1.32
     disabling
    1.25
     Corps
    1.25
     âĸ
    1.21
    ius
    1.20
    NESS
    1.20
    sein
    1.19
     WARRANTIES
    1.18
    Activations Density 0.052%

    No Known Activations