© 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. 11195
    Prev
    Next
    INDEX
    Explanations

    punctuation and inquiry marks

    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
    156
    +0.47
    3.1%
    111
    +0.37
    2.5%
    34
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.47
    0.26
    4
    +0.37
    0.26
    111
    +0.12
    0.24
    Negative Logits
    creen
    -1.60
    CDATA
    -1.40
    ystem
    -1.34
    achine
    -1.33
    uary
    -1.33
    heets
    -1.29
    ftware
    -1.26
    nier
    -1.26
    icture
    -1.26
    ?).
    -1.25
    POSITIVE LOGITS
    į
    2.92
    ²
    2.60
    ¶
    2.58
    Ń
    2.49
    ī
    2.47
    Ĩ
    2.44
    ½
    2.44
    »¿
    2.38
    »
    2.35
    ¸
    2.33
    Activations Density 0.937%

    No Known Activations