© 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. 1-RES-SM
    11. 25696
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their usage in the context of relationships

    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
    156
    +0.24
    1.4%
    1
    +0.11
    0.6%
    221
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.24
    0.10
    137
    +0.11
    0.12
    165
    +0.10
    0.05
    Negative Logits
    anese
    -1.67
    áŁ
    -1.60
    rums
    -1.48
    áŀ
    -1.44
    sten
    -1.38
    forth
    -1.37
    alus
    -1.34
    âĢŁ
    -1.33
    ricular
    -1.33
    ELY
    -1.32
    POSITIVE LOGITS
     previous
    1.74
     bothered
    1.70
    ?_
    1.70
    ?
    1.65
     existing
    1.64
    ?!
    1.61
     yourself
    1.61
     full
    1.56
     curl
    1.48
     entire
    1.47
    Activations Density 1.539%

    No Known Activations