© 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. 1-RES-SM
    11. 29739
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "for"

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    174
    +0.13
    0.7%
    156
    +0.12
    0.7%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.02
    37
    +0.12
    0.01
    178
    +0.11
    0.02
    Negative Logits
    unnumbered
    -2.04
    ĨĴ
    -1.83
    rup
    -1.58
    TON
    -1.55
    shore
    -1.49
    tons
    -1.48
    laid
    -1.48
    ton
    -1.47
    tel
    -1.45
    ¡
    -1.44
    POSITIVE LOGITS
    rels
    1.81
    ilers
    1.73
    rets
    1.69
    ils
    1.68
    xt
    1.66
    enas
    1.64
    ylum
    1.64
    ilities
    1.63
    culus
    1.61
    ility
    1.60
    Activations Density 0.148%

    No Known Activations