© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 30082
    Prev
    Next
    INDEX
    Explanations

    words related to disruption and challenges facing systems or processes

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    195
    +0.13
    0.7%
    465
    +0.12
    0.7%
    33
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.13
    0.12
    465
    +0.12
    0.14
    33
    +0.11
    0.13
    Negative Logits
    nai
    -1.62
    imental
    -1.49
    nier
    -1.48
     diary
    -1.40
    iment
    -1.38
     quarters
    -1.35
     diz
    -1.34
    erals
    -1.31
    ches
    -1.30
     unpublished
    -1.29
    POSITIVE LOGITS
    raise
    1.75
     mine
    1.67
    ifts
    1.60
     ours
    1.52
     theirs
    1.44
    falls
    1.43
    ifically
    1.41
    ift
    1.40
    visibility
    1.40
     acquisition
    1.40
    Activations Density 2.034%

    No Known Activations