© 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. 1-RES-SM
    11. 28129
    Prev
    Next
    INDEX
    Explanations

    phrases related to future intentions and plans

    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
    310
    +0.13
    0.7%
    160
    +0.12
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.07
    310
    +0.12
    0.04
    435
    +0.12
    0.04
    Negative Logits
    Ĵ
    -2.52
    »
    -2.40
    Ļª
    -2.35
    İ
    -2.30
    į
    -2.26
    ¼
    -2.20
    ↵
    -2.20
    <|outofrange|>
    -2.20
    -2.20
    ↵
    -2.20
    POSITIVE LOGITS
     someday
    1.81
     fires
    1.55
    fit
    1.53
     ever
    1.47
     mine
    1.43
    opter
    1.42
    otherwise
    1.36
    kee
    1.35
     demol
    1.33
    ifer
    1.31
    Activations Density 1.076%

    No Known Activations