© 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. 31815
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to software or browser functionality

    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
    186
    +0.18
    1.0%
    393
    +0.12
    0.7%
    97
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.09
    38
    +0.12
    0.06
    450
    +0.12
    0.09
    Negative Logits
    ops
    -1.59
     receives
    -1.34
     traveled
    -1.33
    ids
    -1.31
    itals
    -1.29
    ellen
    -1.29
     .=
    -1.29
     temple
    -1.27
    icates
    -1.27
     travelled
    -1.26
    POSITIVE LOGITS
    º
    2.15
    ¿½
    2.13
    ł
    2.04
    ´
    2.03
    ļ
    2.01
    ĨĴ
    2.01
    ¦
    1.92
    ŀ
    1.91
    ²
    1.86
    ĸ
    1.82
    Activations Density 4.797%

    No Known Activations