© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11040
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming structures

    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
    12
    +0.17
    1.0%
    153
    +0.16
    0.9%
    198
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.17
    0.13
    153
    +0.16
    0.07
    204
    +0.14
    0.12
    Negative Logits
    ħ
    -1.62
     DOI
    -1.62
    į
    -1.47
    «
    -1.46
    Ĥ¬
    -1.46
     ***
    -1.45
    )\].
    -1.44
    ¶
    -1.44
    Ń
    -1.43
     visitation
    -1.43
    POSITIVE LOGITS
    leftarrow
    1.54
     succeed
    1.50
    ILITY
    1.46
    ithmic
    1.46
    acious
    1.45
    rah
    1.40
    mouth
    1.33
    longrightarrow
    1.29
     suffice
    1.28
     dishes
    1.27
    Activations Density 3.623%

    No Known Activations