© 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. 26955
    Prev
    Next
    INDEX
    Explanations

    tips and advice related to various 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/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
    249
    +0.12
    0.7%
    485
    +0.12
    0.7%
    351
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.12
    0.02
    472
    +0.12
    0.02
    351
    +0.12
    0.02
    Negative Logits
    Ĥ
    -2.33
    Ĥ¬
    -2.32
    Ł
    -2.21
    Īĺ
    -2.15
    ĥ½
    -2.14
    ©
    -2.09
    Ī
    -2.06
    ¶
    -1.97
    ĸ´
    -1.92
    °
    -1.92
    POSITIVE LOGITS
    tip
    2.16
    sters
    2.08
    pin
    2.04
    ups
    2.00
    oslav
    1.88
    ologies
    1.82
    nik
    1.80
    ulations
    1.78
    shots
    1.76
    ulates
    1.73
    Activations Density 0.216%

    No Known Activations