© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to systems and integration

    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
    72
    +0.23
    1.3%
    98
    +0.13
    0.7%
    302
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.23
    0.12
    408
    +0.13
    0.11
    403
    +0.13
    0.07
    Negative Logits
    ĻĤ
    -4.85
    ¤
    -4.26
    Ĥ
    -4.20
    ª
    -4.16
    Ļ
    -4.13
    ²
    -4.05
    ĸ´
    -4.03
    ĸ
    -4.00
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -3.97
    ļ
    -3.96
    POSITIVE LOGITS
    ately
    1.64
    inally
    1.61
    ically
    1.45
    ally
    1.43
     duty
    1.39
    arily
    1.38
    carbox
    1.34
    yzed
    1.32
    argin
    1.30
    own
    1.29
    Activations Density 4.411%

    No Known Activations