© 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. 26656
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is incorrect or problematic

    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
    488
    +0.14
    0.8%
    260
    +0.13
    0.7%
    248
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.14
    0.03
    260
    +0.13
    0.03
    488
    +0.13
    0.03
    Negative Logits
    itol
    -1.61
    ilde
    -1.56
    augh
    -1.52
    LinearLayout
    -1.43
    CRO
    -1.42
    ocity
    -1.40
    ints
    -1.39
    auc
    -1.38
    oxacin
    -1.36
    ings
    -1.33
    POSITIVE LOGITS
    Ł
    1.90
    ĻĤ
    1.69
     reasons
    1.61
    Ģ
    1.60
     wording
    1.54
    gered
    1.54
    ť
    1.53
     tune
    1.51
    ·
    1.49
     please
    1.49
    Activations Density 0.085%

    No Known Activations