© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29957
    Prev
    Next
    INDEX
    Explanations

    words indicating the existence of something

    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
    127
    +0.13
    0.7%
    241
    +0.12
    0.7%
    219
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.03
    343
    +0.12
    0.02
    335
    +0.11
    0.02
    Negative Logits
    Īĺ
    -3.75
    ŀ
    -3.37
    ľ
    -3.37
    ĩ
    -3.34
    Ĥ¬
    -3.22
    ¡
    -3.21
    ļ
    -3.19
    Ĥ
    -3.16
    £
    -3.13
    ı
    -3.12
    POSITIVE LOGITS
     quo
    1.82
     Of
    1.69
    ality
    1.69
     of
    1.64
    ato
    1.63
    itive
    1.59
    bone
    1.58
    ino
    1.52
    elling
    1.50
    idia
    1.49
    Activations Density 0.134%

    No Known Activations