© 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. 14672
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "AN" in various contexts

    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
    30
    +0.13
    0.7%
    375
    +0.12
    0.6%
    168
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.13
    0.04
    493
    +0.12
    0.04
    154
    +0.11
    0.04
    Negative Logits
    olar
    -1.80
    ering
    -1.70
    lect
    -1.54
    med
    -1.53
    aint
    -1.52
    matically
    -1.51
    xygen
    -1.44
    olated
    -1.42
    leton
    -1.40
    hift
    -1.38
    POSITIVE LOGITS
    DR
    2.38
    ISH
    2.36
    NER
    2.13
    ISHED
    2.13
    TERN
    2.10
    CHO
    2.00
    ITY
    1.99
    ESE
    1.99
    OV
    1.96
    DA
    1.95
    Activations Density 0.164%

    No Known Activations