© 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. 4-RES-SM
    11. 10797
    Prev
    Next
    INDEX
    Explanations

    references to programming and hardware specifications

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    282
    +0.17
    0.9%
    349
    +0.14
    0.8%
    459
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.17
    0.06
    203
    +0.14
    0.04
    349
    +0.12
    0.07
    Negative Logits
    achi
    -1.50
    icult
    -1.33
     Chile
    -1.32
    ibility
    -1.27
    chers
    -1.25
     Mol
    -1.25
    ophagus
    -1.22
    vic
    -1.19
    hest
    -1.16
    abella
    -1.15
    POSITIVE LOGITS
     D
    4.16
    D
    3.51
     DD
    3.37
     d
    3.37
    Ds
    3.36
    DD
    3.33
     DCA
    3.00
     DA
    2.99
    d
    2.97
     DS
    2.96
    Activations Density 2.168%

    No Known Activations