© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11387
    Prev
    Next
    INDEX
    Explanations

    references to transitions or changes in context

    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
    156
    +0.14
    0.8%
    404
    +0.13
    0.7%
    143
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.14
    0.01
    115
    +0.13
    0.01
    5
    +0.11
    0.01
    Negative Logits
    Ļ
    -2.56
    Ľ
    -2.38
    ¤
    -2.36
    ĻĤ
    -2.35
    »¿
    -2.28
    ĸ´
    -2.26
    ¿½
    -2.25
    ĥ½
    -2.23
    į
    -2.17
    İ
    -2.13
    POSITIVE LOGITS
     between
    1.89
     occurs
    1.88
     period
    1.82
     phase
    1.77
     occurred
    1.73
     stage
    1.72
    ight
    1.67
     phases
    1.64
     periods
    1.62
     dipole
    1.59
    Activations Density 0.109%

    No Known Activations