© 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. 13517
    Prev
    Next
    INDEX
    Explanations

    key legal terms and conditions related to criminal proceedings

    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
    121
    +0.19
    1.1%
    6
    +0.19
    1.1%
    12
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.19
    0.11
    6
    +0.19
    0.13
    12
    +0.18
    0.13
    Negative Logits
    ŀ
    -1.65
    °
    -1.62
    ª
    -1.58
    ¦
    -1.56
     herself
    -1.54
    ¸
    -1.54
    «
    -1.50
    ĻĤ
    -1.49
    ľ
    -1.45
    ´
    -1.40
    POSITIVE LOGITS
    $)
    1.71
    hin
    1.69
    ']))
    1.61
    )$-
    1.61
     intended
    1.54
    }$)
    1.53
    ipes
    1.52
    $),
    1.51
    ');
    1.51
    umes
    1.51
    Activations Density 3.384%

    No Known Activations