© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-SM
    11. 27294
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or seek assistance

    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
    156
    +0.22
    1.2%
    503
    +0.13
    0.7%
    416
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.22
    -0.02
    165
    +0.13
    0.01
    85
    +0.12
    0.04
    Negative Logits
    »¿
    -2.54
    Ħ
    -2.50
    <|outofrange|>
    -2.40
    ↵
    -2.40
    -2.40
    ↵
    -2.40
    -2.40
    ↵
    -2.40
     ↵
    -2.40
    č↵č↵
    -2.40
    POSITIVE LOGITS
     wrong
    1.56
    ")]
    1.49
     *"
    1.48
     himself
    1.46
    vist
    1.44
    ?",
    1.40
     badly
    1.40
    )}$
    1.39
    )\]
    1.38
     damn
    1.37
    Activations Density 1.133%

    No Known Activations