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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28086
    Prev
    Next
    INDEX
    Explanations

    text structured as scientific abstracts or formal summaries

    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
    111
    +0.15
    0.8%
    87
    +0.14
    0.8%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.01
    249
    +0.14
    0.01
    189
    +0.12
    0.01
    Negative Logits
    dad
    -1.73
    done
    -1.55
    hores
    -1.54
    ÅĽci
    -1.44
    fax
    -1.43
     royalty
    -1.42
     fence
    -1.39
     lasted
    -1.39
    phone
    -1.38
    hold
    -1.38
    POSITIVE LOGITS
    TRODUCTION
    1.96
     advances
    1.59
     attacks
    1.58
    ympt
    1.57
    cribing
    1.50
    ociation
    1.50
    theless
    1.49
    uric
    1.44
    ensive
    1.41
    existence
    1.40
    Activations Density 0.047%

    No Known Activations