© 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. 9992
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly those identified by the term "Her."

    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
    •Gradient Fine-tune
    Interference Feature of F.6674, I-0.3567.

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.13
    0.7%
    410
    +0.11
    0.6%
    21
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.13
    0.02
    410
    +0.11
    0.03
    3
    +0.11
    0.01
    Negative Logits
    ordin
    -1.69
     others
    -1.55
     matter
    -1.55
    edly
    -1.55
     fact
    -1.42
    ÄŁ
    -1.41
    ener
    -1.40
     ya
    -1.39
     contrary
    -1.38
     theirs
    -1.37
    POSITIVE LOGITS
     Majesty
    2.73
    itage
    2.70
    cules
    2.58
    odot
    2.38
    oku
    2.35
    rera
    2.33
    itance
    2.26
    bst
    2.18
    ½
    2.16
     Excell
    2.10
    Activations Density 0.180%

    No Known Activations