© 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. 4-RES-SM
    11. 13746
    Prev
    Next
    INDEX
    Explanations

    elements related to data handling and processing in code

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.12
    0.7%
    491
    +0.10
    0.5%
    41
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.12
    -0.01
    203
    +0.10
    0.03
    30
    +0.10
    0.01
    Negative Logits
     ÂĹ
    -1.78
    )[@
    -1.77
    `:
    -1.74
    ,--
    -1.72
     -
    -1.71
    )](#
    -1.66
    :"
    -1.63
    âĢķ
    -1.59
    :--
    -1.57
     ([
    -1.55
    POSITIVE LOGITS
     );
    2.05
     His
    1.74
     his
    1.57
     backward
    1.53
    \]\].
    1.47
     him
    1.45
     faculty
    1.42
     He
    1.41
     </
    1.38
    his
    1.36
    Activations Density 0.720%

    No Known Activations