© 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. 1-RES-SM
    11. 27088
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tag structures in the text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    59
    +0.12
    0.8%
    482
    +0.10
    0.6%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.07
    416
    +0.10
    0.10
    165
    +0.10
    0.06
    Negative Logits
    .[]{
    -1.51
     %}
    -1.50
    Errno
    -1.40
    Bye
    -1.37
    .’
    -1.34
     her
    -1.30
    walk
    -1.29
    .](
    -1.28
     mer
    -1.28
    ).](
    -1.26
    POSITIVE LOGITS
    achus
    1.68
    ·¸
    1.58
    ktop
    1.56
    ĥ½
    1.55
    <|outofrange|>
    1.45
    1.45
     ↵
    1.45
    <|outofrange|>
    1.45
    ↵↵
    1.45
    ↵
    1.45
    Activations Density 3.647%

    No Known Activations