© 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. 24265
    Prev
    Next
    INDEX
    Explanations

    terms related to multifaceted or complex subjects

    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
    40
    +0.15
    0.9%
    203
    +0.15
    0.9%
    9
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.15
    0.02
    118
    +0.15
    0.01
    203
    +0.14
    0.01
    Negative Logits
    inson
    -1.62
    avage
    -1.56
    hering
    -1.55
     signs
    -1.41
     expiration
    -1.40
    oving
    -1.40
     .=
    -1.39
    mpty
    -1.39
    denly
    -1.39
    lasses
    -1.38
    POSITIVE LOGITS
    ĻĤ
    3.99
    Ĵ
    3.76
    Ħ
    3.71
    Ļª
    3.69
    ³
    3.58
    ·
    3.56
    ±
    3.56
    ģ
    3.56
    ĨĴ
    3.53
    £
    3.51
    Activations Density 0.055%

    No Known Activations