© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27175
    Prev
    Next
    INDEX
    Explanations

    specific types of activities or components related to coin collecting and categorization

    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
    23
    +0.19
    1.1%
    70
    +0.12
    0.6%
    402
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.15
    478
    +0.12
    0.00
    418
    +0.11
    -0.00
    Negative Logits
    Ĭ
    -2.41
    ĺ
    -2.34
    İ
    -2.17
    ŀ
    -2.16
    ĭ
    -2.14
    ¶
    -2.10
    Ļ
    -2.08
    ģ
    -2.07
    Į
    -2.06
    Ĩ
    -2.06
    POSITIVE LOGITS
     sizes
    1.89
    including
    1.65
     sorted
    1.59
     including
    1.56
     exceptions
    1.53
     varieties
    1.53
     ones
    1.53
     grouped
    1.53
     nights
    1.52
     various
    1.51
    Activations Density 2.516%

    No Known Activations