© 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. 29824
    Prev
    Next
    INDEX
    Explanations

    phrases that imply negativity or criticism

    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
    452
    +0.14
    0.8%
    313
    +0.13
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.14
    0.05
    452
    +0.13
    0.04
    203
    +0.12
    0.05
    Negative Logits
    umns
    -1.90
    ipation
    -1.64
    riction
    -1.61
    ILITY
    -1.58
    /">
    -1.56
    -%
    -1.53
    ributes
    -1.53
    atically
    -1.52
    orect
    -1.50
    -"
    -1.50
    POSITIVE LOGITS
     means
    1.45
    gard
    1.39
    ]{.
    1.36
    unnumbered
    1.36
    esque
    1.33
    known
    1.30
    by
    1.30
     peers
    1.28
    squared
    1.28
    fold
    1.26
    Activations Density 0.241%

    No Known Activations