© 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. 27928
    Prev
    Next
    INDEX
    Explanations

    words related to names or naming

    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
    +0.18
    1.0%
    22
    +0.13
    0.7%
    287
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.18
    0.03
    269
    +0.13
    0.02
    58
    +0.13
    0.02
    Negative Logits
    ı
    -2.69
    Ĩ
    -1.93
    -1.90
    -1.90
    <|outofrange|>
    -1.90
    -1.90
    -1.90
    <|outofrange|>
    -1.90
    ↵            ↵
    -1.90
    -1.90
    POSITIVE LOGITS
    paces
    2.67
    erver
    2.25
    pace
    2.13
    paced
    2.04
    urname
    1.98
    uffix
    1.79
     surname
    1.79
    erve
    1.70
    aurus
    1.67
    hell
    1.66
    Activations Density 0.214%

    No Known Activations