© 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. 29688
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and communal aspects

    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
    497
    +0.12
    0.7%
    438
    +0.11
    0.6%
    117
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.12
    0.01
    445
    +0.11
    0.00
    92
    +0.11
    0.01
    Negative Logits
    oxin
    -1.62
     mouse
    -1.55
    izer
    -1.53
    ities
    -1.52
    izations
    -1.50
    à°¿
    -1.49
    izing
    -1.48
    ")]
    -1.48
    rapeutics
    -1.48
    irectional
    -1.47
    POSITIVE LOGITS
     accession
    1.62
    éric
    1.58
     rue
    1.50
     south
    1.49
     north
    1.49
     coron
    1.47
     archive
    1.47
     anonym
    1.46
     Ãī
    1.44
     Ãģ
    1.43
    Activations Density 0.057%

    No Known Activations