© 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 EvalsExportsinterp-engineNEWAPI 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. 9448
    Prev
    Next
    INDEX
    Explanations

    markup and structural elements in a document

    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
    78
    +0.29
    1.8%
    21
    +0.20
    1.3%
    397
    +0.20
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.29
    0.14
    78
    +0.20
    0.02
    21
    +0.20
    0.07
    Negative Logits
    inating
    -1.61
    izing
    -1.51
    rangian
    -1.44
    iating
    -1.42
    ging
    -1.41
    igating
    -1.40
    CLUSION
    -1.39
    iferase
    -1.35
    dling
    -1.35
    ying
    -1.34
    POSITIVE LOGITS
     meant
    1.22
    stro
    1.17
     hell
    1.16
     kidding
    1.16
    castle
    1.15
    &#
    1.15
     talk
    1.15
     Ki
    1.14
     clad
    1.13
     kw
    1.10
    Activations Density 2.269%

    No Known Activations