© 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. 27551
    Prev
    Next
    INDEX
    Explanations

    references to authority and official documentation in a religious or legal context

    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
    313
    +0.11
    0.6%
    403
    +0.11
    0.6%
    302
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.11
    0.17
    358
    +0.11
    0.23
    403
    +0.11
    0.13
    Negative Logits
    ·¸
    -3.03
    ı
    -2.52
    «
    -2.48
    ¬
    -2.41
    ħ
    -2.41
    ŀ
    -2.37
    ¡
    -2.34
    ķ
    -2.33
    ĸ´
    -2.31
    ļ
    -2.31
    POSITIVE LOGITS
    .).
    2.41
    '.
    1.97
    ].
    1.96
    .]
    1.95
    ».
    1.89
    ’.
    1.85
    ]{}.
    1.79
    ]."
    1.79
    .
    1.79
    .''
    1.73
    Activations Density 8.144%

    No Known Activations