© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11170
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to managing or manipulating data

    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
    320
    +0.18
    1.0%
    323
    +0.12
    0.7%
    176
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.18
    0.15
    33
    +0.12
    0.14
    490
    +0.12
    0.09
    Negative Logits
    ħ
    -2.77
    »
    -2.76
    ij
    -2.74
    ¿½
    -2.62
    ±
    -2.61
    Ļ
    -2.52
    Ĩ
    -2.47
    ¹
    -2.46
    ·¸
    -2.42
    §
    -2.42
    POSITIVE LOGITS
     respectively
    1.84
     portions
    1.66
     vacated
    1.57
    .\[[@
    1.55
     alike
    1.53
     Additional
    1.46
    upal
    1.44
    iscuss
    1.42
    bage
    1.42
     participated
    1.41
    Activations Density 4.864%

    No Known Activations