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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11651
    Prev
    Next
    INDEX
    Explanations

    references to years and associated copyright information

    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
    286
    +0.13
    0.7%
    240
    +0.12
    0.7%
    469
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.13
    0.03
    450
    +0.12
    0.03
    253
    +0.12
    0.02
    Negative Logits
    Ł
    -2.09
    ħ
    -2.00
    Į
    -1.96
    ¹
    -1.91
    »¿
    -1.89
    ľĵ
    -1.83
    ¨
    -1.77
    į
    -1.77
    ij
    -1.74
    ķ
    -1.73
    POSITIVE LOGITS
    bos
    1.35
    boro
    1.33
    ISING
    1.27
    baum
    1.27
    ilinear
    1.22
    vell
    1.20
    imon
    1.20
     Olympics
    1.20
     WARRANTIES
    1.19
     FIN
    1.18
    Activations Density 0.207%

    No Known Activations