© 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. 13505
    Prev
    Next
    INDEX
    Explanations

    mentions of people or characters related to personal experiences or narratives

    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
    17
    +0.23
    1.3%
    302
    +0.18
    1.0%
    479
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.23
    0.02
    479
    +0.18
    0.07
    86
    +0.18
    0.09
    Negative Logits
    ocene
    -1.69
    falls
    -1.47
    cludes
    -1.46
    orems
    -1.45
    oprote
    -1.45
     justice
    -1.45
     purification
    -1.44
    othermal
    -1.44
    filters
    -1.42
    ieurs
    -1.39
    POSITIVE LOGITS
    enne
    1.44
    wen
    1.43
    )\].
    1.37
     Interests
    1.33
    inch
    1.33
     instant
    1.24
    teenth
    1.24
    bone
    1.22
    ello
    1.22
     positions
    1.20
    Activations Density 2.513%

    No Known Activations