Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29087
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and concepts

    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
    98
    +0.15
    0.8%
    282
    +0.13
    0.7%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.09
    404
    +0.13
    0.10
    407
    +0.13
    0.08
    Negative Logits
    ian
    -1.52
    berg
    -1.42
    ring
    -1.42
     clashes
    -1.40
    wide
    -1.40
    hold
    -1.36
    pic
    -1.34
    =.
    -1.33
    ruptcy
    -1.33
     dyst
    -1.31
    POSITIVE LOGITS
    MOESM
    2.26
    thems
    1.81
    FPar
    1.71
     each
    1.59
    supplementary
    1.58
     ourselves
    1.58
    fered
    1.58
     behalf
    1.56
    ---|---|---
    1.55
     Fig
    1.53
    Activations Density 0.647%

    No Known Activations