© 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. 27071
    Prev
    Next
    INDEX
    Explanations

    the word "reserve" and its variations, indicating a focus on reservations or related concepts

    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
    410
    +0.13
    0.7%
    307
    +0.13
    0.7%
    86
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.13
    0.03
    410
    +0.13
    0.04
    86
    +0.11
    0.03
    Negative Logits
     blame
    -1.89
    pora
    -1.46
     deserve
    -1.45
     Nigerian
    -1.43
    terest
    -1.42
     Nigeria
    -1.39
    plasia
    -1.38
    ffect
    -1.36
     situation
    -1.36
    ↵³³
    -1.35
    POSITIVE LOGITS
    ¦
    3.12
    ¨
    2.94
    ©
    2.74
    Ģ
    2.67
    §
    2.67
    ´
    2.65
    ij
    2.62
    ²
    2.58
    ¤
    2.54
    Ĩ
    2.53
    Activations Density 0.232%

    No Known Activations