© 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. 25516
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticism in discussions

    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
    491
    +0.14
    0.8%
    497
    +0.13
    0.7%
    249
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.07
    50
    +0.13
    0.06
    249
    +0.12
    0.05
    Negative Logits
    -"
    -1.66
    -
    -1.66
    -(
    -1.58
    onic
    -1.56
    inux
    -1.50
    -*
    -1.46
    obic
    -1.45
    umps
    -1.44
    omy
    -1.41
    /#
    -1.39
    POSITIVE LOGITS
    arte
    1.60
    )—
    1.48
    eur
    1.42
    )];
    1.41
    )));
    1.39
    bred
    1.33
    orbit
    1.32
    arb
    1.31
    ze
    1.30
    appointed
    1.30
    Activations Density 0.585%

    No Known Activations