© 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 EvalsExportsinterp-engineNEWAPI 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. 13401
    Prev
    Next
    INDEX
    Explanations

    instances of the word "guest" in various contexts

    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
    156
    +0.19
    1.1%
    142
    +0.14
    0.8%
    288
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.19
    0.02
    268
    +0.14
    0.02
    174
    +0.12
    0.02
    Negative Logits
    ĥ½
    -3.44
    ·
    -3.24
    ¯
    -3.17
    -3.14
              ↵
    -3.14
    <|outofrange|>
    -3.14
    č↵
    -3.14
    -3.14
    -3.14
    -3.14
    POSITIVE LOGITS
    esses
    2.02
    book
    1.84
    tails
    1.81
    doms
    1.71
    grounds
    1.71
    houses
    1.69
    books
    1.64
    holder
    1.61
    face
    1.61
    eries
    1.56
    Activations Density 0.175%

    No Known Activations