© 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. 32115
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in"

    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
    136
    +0.16
    0.9%
    66
    +0.14
    0.8%
    434
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.16
    0.05
    82
    +0.14
    0.03
    86
    +0.14
    0.04
    Negative Logits
     =>
    -1.85
    s
    -1.73
    =>
    -1.71
     sender
    -1.52
    tin
    -1.51
    eer
    -1.49
    tet
    -1.38
     few
    -1.33
    ftime
    -1.33
    xygen
    -1.32
    POSITIVE LOGITS
    stitution
    2.44
    stitutional
    2.27
    clusive
    2.27
    flu
    2.17
    ventory
    2.09
    frastructure
    2.08
    hibition
    1.98
    eral
    1.90
    kered
    1.90
    ning
    1.89
    Activations Density 0.216%

    No Known Activations