Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29357
    Prev
    Next
    INDEX
    Explanations

    references to liquid substances or their properties

    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
    156
    +0.22
    1.3%
    304
    +0.14
    0.8%
    495
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.22
    0.02
    495
    +0.14
    0.01
    18
    +0.12
    0.01
    Negative Logits
    cess
    -1.75
     ours
    -1.61
     founder
    -1.60
    rior
    -1.56
     passer
    -1.47
    nae
    -1.44
    ÏħÏĦ
    -1.42
     proud
    -1.42
    TRODUCTION
    -1.42
    Ñĸд
    -1.38
    POSITIVE LOGITS
    Ĵ
    2.07
    ľ
    1.97
    ģ
    1.89
    itation
    1.89
    ²
    1.88
    ī
    1.87
     chromatography
    1.87
    ¿½
    1.79
    ħ
    1.79
    »
    1.77
    Activations Density 0.066%

    No Known Activations