© 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. 1-RES-SM
    11. 28685
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    415
    +0.14
    0.8%
    54
    +0.13
    0.7%
    290
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.14
    0.03
    334
    +0.13
    0.03
    415
    +0.12
    0.03
    Negative Logits
    º
    -2.11
    ĭ
    -2.01
    Ĩ
    -2.00
    ¿½
    -1.94
    ¿
    -1.93
    Ļª
    -1.92
    ¶
    -1.90
    ¬
    -1.89
    £
    -1.88
    ²
    -1.87
    POSITIVE LOGITS
    giving
    2.10
    reflect
    1.51
     incident
    1.45
     gesture
    1.41
     designers
    1.39
     exemplary
    1.38
     cond
    1.37
    dro
    1.34
     rins
    1.33
     toll
    1.33
    Activations Density 0.175%

    No Known Activations