© 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. 29086
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and milestones in a narrative

    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
    347
    +0.12
    0.7%
    365
    +0.12
    0.7%
    129
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.12
    0.13
    376
    +0.12
    0.06
    148
    +0.12
    0.04
    Negative Logits
    keit
    -1.72
    ington
    -1.52
    aliana
    -1.50
    consin
    -1.44
     locally
    -1.43
     prominently
    -1.41
    >;
    -1.41
    soever
    -1.39
    chst
    -1.38
    emer
    -1.36
    POSITIVE LOGITS
     lesson
    1.70
    ĥ½
    1.60
    IJ
    1.55
    £
    1.53
    ·
    1.50
    »
    1.49
     ↵
    1.45
    <|outofrange|>
    1.45
    <|outofrange|>
    1.45
    ↵  Âł
    1.45
    Activations Density 9.225%

    No Known Activations