© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11360
    Prev
    Next
    INDEX
    Explanations

    financial figures related to relief efforts and government actions

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.25
    1.5%
    274
    +0.16
    0.9%
    466
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.25
    0.15
    466
    +0.16
    0.14
    418
    +0.13
    0.03
    Negative Logits
     âĻª"
    -2.38
    )—
    -2.36
    ÂĹ
    -2.35
    —
    -2.29
    .^[@
    -2.23
     <-
    -2.08
     "âĻª
    -2.08
    ,^[@
    -2.06
    —.
    -1.88
     ÂĹ
    -1.85
    POSITIVE LOGITS
    ĥ½
    2.69
    ↵↵
    2.36
    <|outofrange|>
    2.36
    <|outofrange|>
    2.36
    ↵
    2.36
    2.36
    ↵↵
    2.36
    2.36
    č↵č↵
    2.36
     ↵
    2.36
    Activations Density 3.298%

    No Known Activations