© 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. 30867
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their associated operations

    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
    284
    +0.15
    0.9%
    281
    +0.14
    0.8%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.04
    436
    +0.14
    0.08
    369
    +0.13
    0.05
    Negative Logits
    ı
    -4.07
    -3.99
    <|outofrange|>
    -3.99
    ↵↵
    -3.99
    -3.99
    ↵
    -3.99
    ↵↵
    -3.99
    -3.99
    -3.99
    č↵
    -3.99
    POSITIVE LOGITS
    otted
    1.78
    adr
    1.51
    âĢ²,
    1.50
    itars
    1.42
    owed
    1.41
    imuth
    1.41
    ucked
    1.40
    NaN
    1.36
    eeper
    1.34
    digit
    1.32
    Activations Density 0.985%

    No Known Activations