© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism

    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
    484
    +0.15
    0.9%
    497
    +0.13
    0.7%
    491
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.15
    0.11
    266
    +0.13
    0.08
    129
    +0.12
    0.02
    Negative Logits
    "}](#
    -1.93
    :`
    -1.77
    ,[@
    -1.62
    )[@
    -1.58
    orbent
    -1.56
    tes
    -1.50
    ].)
    -1.49
    geb
    -1.46
    idden
    -1.45
     ranged
    -1.45
    POSITIVE LOGITS
    Ī
    2.82
    ĻĤ
    2.79
    ³
    2.78
    Ŀ
    2.75
    ŀ
    2.72
    ¿½
    2.61
    ´
    2.60
    ¿
    2.49
    ĺ
    2.41
    º
    2.38
    Activations Density 0.888%

    No Known Activations