© 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. 31085
    Prev
    Next
    INDEX
    Explanations

    code and configuration elements related to security and data structure definitions

    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
    287
    +0.11
    0.6%
    394
    +0.11
    0.6%
    11
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.11
    0.09
    85
    +0.11
    0.05
    11
    +0.11
    0.05
    Negative Logits
    )].
    -2.26
    )](
    -2.05
    .]{}
    -1.92
    rbrack
    -1.87
    ).](
    -1.86
    )]
    -1.83
    ")]
    -1.80
    )**
    -1.75
    )](#
    -1.69
    .](
    -1.67
    POSITIVE LOGITS
    ¼
    2.28
    Ļ
    2.16
    ®
    2.00
    ª
    1.91
    Ľ
    1.91
    ·
    1.90
    ī
    1.89
    ľ
    1.84
    ¦
    1.83
    Ģ
    1.81
    Activations Density 0.516%

    No Known Activations