© 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. 12540
    Prev
    Next
    INDEX
    Explanations

    references to photographs and photo collections

    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
    100
    +0.16
    0.9%
    51
    +0.13
    0.7%
    372
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.16
    0.05
    46
    +0.13
    0.02
    372
    +0.12
    0.02
    Negative Logits
    Īĺ
    -3.50
    ¯
    -3.12
    ķ
    -2.81
    «
    -2.81
    Ł
    -2.76
    ľĵ
    -2.76
    ĭ
    -2.75
    ĵ
    -2.72
    ´
    -2.71
    §
    -2.67
    POSITIVE LOGITS
    jpeg
    2.56
    ictures
    2.09
     pics
    1.91
     caption
    1.90
    journal
    1.90
     gallery
    1.89
    clamation
    1.89
    aced
    1.88
    image
    1.85
     Caption
    1.84
    Activations Density 0.225%

    No Known Activations