© 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. 2-RES-SM
    11. 27681
    Prev
    Next
    INDEX
    Explanations

    Python-related terms 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
    269
    +0.13
    0.7%
    50
    +0.11
    0.6%
    135
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.13
    0.04
    504
    +0.11
    0.03
    445
    +0.11
    0.02
    Negative Logits
    ifiable
    -1.65
    izable
    -1.60
    icolor
    -1.57
    izability
    -1.51
    cribe
    -1.51
     impossible
    -1.47
    ainties
    -1.45
     horizon
    -1.43
    icable
    -1.40
    )|$(
    -1.36
    POSITIVE LOGITS
    outube
    2.18
    ellow
    1.92
    eah
    1.87
    oke
    1.84
    ahoo
    1.83
    ounger
    1.78
    nergy
    1.66
    ears
    1.63
    rosine
    1.62
    STEM
    1.60
    Activations Density 0.197%

    No Known Activations