© 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. 28694
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence or participation in various contexts

    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
    36
    +0.13
    0.7%
    444
    +0.13
    0.7%
    69
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.08
    36
    +0.13
    0.05
    448
    +0.12
    0.04
    Negative Logits
    asian
    -1.58
    uis
    -1.56
    aday
    -1.51
     Sierra
    -1.50
    adian
    -1.45
    arc
    -1.44
    iana
    -1.43
    qua
    -1.43
    tion
    -1.42
    than
    -1.42
    POSITIVE LOGITS
    ETHOD
    1.62
     bets
    1.55
     \"
    1.50
    že
    1.48
    DER
    1.47
    juvant
    1.39
     jeopardy
    1.38
     antibiotics
    1.35
     stret
    1.34
     tack
    1.34
    Activations Density 0.699%

    No Known Activations