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. 11716
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly lists and arrays

    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
    +0.17
    1.0%
    412
    +0.15
    0.9%
    489
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.17
    0.03
    17
    +0.15
    0.01
    41
    +0.14
    0.02
    Negative Logits
    ĵ
    -1.99
    pires
    -1.90
    §
    -1.63
    ļ
    -1.62
    µ
    -1.57
    ľĵ
    -1.54
    ¤
    -1.53
    IJ
    -1.47
    protobuf
    -1.46
    role
    -1.42
    POSITIVE LOGITS
    ening
    2.22
    horn
    1.92
     Items
    1.85
    eners
    1.84
    orio
    1.70
    ured
    1.70
    ener
    1.67
    etable
    1.66
     Caption
    1.62
     item
    1.60
    Activations Density 0.084%

    No Known Activations