© 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. 25968
    Prev
    Next
    INDEX
    Explanations

    references to directory paths and file management 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
    91
    +0.12
    0.7%
    211
    +0.12
    0.7%
    110
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.12
    0.03
    17
    +0.12
    0.01
    211
    +0.12
    0.02
    Negative Logits
    ureus
    -1.89
    ķ
    -1.85
    Ķ
    -1.52
    grade
    -1.52
     assumptions
    -1.51
    ery
    -1.43
    Īĺ
    -1.42
     welcome
    -1.39
     kindly
    -1.38
    ĵ
    -1.38
    POSITIVE LOGITS
    ichlet
    2.74
    itto
    2.11
    iffe
    1.64
    itti
    1.64
    ship
    1.59
    esan
    1.59
    icile
    1.58
    =”
    1.54
    :/
    1.53
    ham
    1.53
    Activations Density 0.150%

    No Known Activations