© 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. 2-RES-SM
    11. 30367
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations and scientific notation

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    47
    +0.19
    1.0%
    320
    +0.17
    1.0%
    343
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.19
    0.10
    325
    +0.17
    0.07
    79
    +0.12
    0.05
    Negative Logits
    among
    -1.62
    iced
    -1.59
    )</
    -1.52
    ago
    -1.49
    araoh
    -1.44
    ento
    -1.44
    aria
    -1.44
    eligible
    -1.43
    confirmed
    -1.42
    league
    -1.41
    POSITIVE LOGITS
    ESULT
    1.83
    ·¸
    1.75
    ·
    1.75
    ¦
    1.75
    č↵
    1.72
    1.72
    1.72
    1.72
    ↵
    1.72
    1.72
    Activations Density 1.297%

    No Known Activations