© 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 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. 10366
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and references

    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
    111
    +0.15
    0.9%
    385
    +0.13
    0.8%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.15
    0.02
    21
    +0.13
    0.02
    221
    +0.12
    0.02
    Negative Logits
    )."
    -1.57
     guitar
    -1.57
    !'
    -1.51
    ogether
    -1.45
    (*
    -1.37
     however
    -1.35
     pipes
    -1.34
    assert
    -1.33
     plating
    -1.33
     plated
    -1.32
    POSITIVE LOGITS
    ¡
    2.66
    «
    2.66
    µ
    2.61
    ij
    2.59
    ¸
    2.58
    ī
    2.52
    Ĩ
    2.47
    ľ
    2.46
    İ
    2.37
    Ŀ
    2.37
    Activations Density 0.087%

    No Known Activations