© 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. 2-RES-SM
    11. 10771
    Prev
    Next
    INDEX
    Explanations

    elements related to visual descriptors and characteristics

    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
    478
    +0.16
    0.9%
    47
    +0.16
    0.9%
    142
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.17
    408
    +0.16
    0.11
    478
    +0.12
    0.01
    Negative Logits
    itud
    -1.93
    ité
    -1.69
    ĻĤ
    -1.64
     ahead
    -1.61
    chair
    -1.56
    naire
    -1.53
    aska
    -1.52
    IFIC
    -1.50
    ariat
    -1.50
    aire
    -1.48
    POSITIVE LOGITS
    )|^
    1.79
     backgrounds
    1.55
    olas
    1.53
    )$-
    1.52
    |^
    1.44
     sizes
    1.44
    ]_{
    1.40
    obiles
    1.39
     widths
    1.39
     their
    1.38
    Activations Density 3.519%

    No Known Activations