© 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 EvalsExportsAPI 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. 10078
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" used in various contexts, particularly in code and logical structures

    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
    478
    +0.15
    0.8%
    284
    +0.13
    0.7%
    38
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.15
    0.03
    434
    +0.13
    0.04
    38
    +0.13
    0.02
    Negative Logits
    ingly
    -1.96
    back
    -1.78
    backs
    -1.72
    sburg
    -1.68
    about
    -1.66
    until
    -1.56
    hes
    -1.54
    rict
    -1.50
    punk
    -1.48
    urn
    -1.47
    POSITIVE LOGITS
    ĸ´
    2.76
    »
    2.69
    Ł
    2.65
    ļ
    2.48
    Ĵ
    2.41
    ¡
    2.40
    »¿
    2.38
    ·¸
    2.35
    ĭ
    2.32
    ↵
    2.31
    Activations Density 0.202%

    No Known Activations