© 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. 1-RES-SM
    11. 25888
    Prev
    Next
    INDEX
    Explanations

    the word "one" in various contexts

    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
    87
    +0.18
    1.0%
    228
    +0.12
    0.7%
    239
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.18
    0.06
    239
    +0.12
    0.05
    249
    +0.12
    0.04
    Negative Logits
    raising
    -1.76
    ting
    -1.59
     align
    -1.44
    orate
    -1.43
    omitempty
    -1.42
    ed
    -1.41
    verter
    -1.38
    ing
    -1.37
    ional
    -1.36
    OUND
    -1.36
    POSITIVE LOGITS
    Īĺ
    2.13
    ĥ
    2.12
    ¾
    2.10
    Ī
    2.09
    ¿½
    2.08
    ¸
    2.07
     hundred
    2.06
    ľ
    1.95
    į
    1.95
    ķ
    1.91
    Activations Density 0.165%

    No Known Activations